Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.7011. Min Range: -15.7011
Max Act: 15.7011. Min Act: -0.1700
Data Index: 2395783 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.7011. Min Range: -15.7011
Max Act: 15.3886. Min Act: -0.1700
Data Index: 1892824 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.7011. Min Range: -15.7011
Max Act: 15.0761. Min Act: -0.1700
Data Index: 1485044 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.9511. Min Act: -0.1700
Data Index: 1892823 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.7636. Min Act: -0.1700
Data Index: 1405979 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.7636. Min Act: -0.1700
Data Index: 4508393 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.7011. Min Act: -0.1700
Data Index: 1294189 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.6386. Min Act: -0.1700
Data Index: 6006434 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5761. Min Act: -0.1700
Data Index: 3363513 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.6386. Min Act: -0.1700
Data Index: 1527096 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5761. Min Act: -0.1700
Data Index: 7960003 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5761. Min Act: -0.1700
Data Index: 2073420 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5761. Min Act: -0.1700
Data Index: 6006433 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5761. Min Act: -0.1700
Data Index: 808524 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.4511. Min Act: -0.1700
Data Index: 2410999 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.5136. Min Act: -0.1700
Data Index: 3824770 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.4511. Min Act: -0.1700
Data Index: 6283834 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.3886. Min Act: -0.1700
Data Index: 6890262 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.3261. Min Act: -0.1700
Data Index: 3563979 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.7011. Min Range: -15.7011
Max Act: 14.3261. Min Act: -0.1700
Data Index: 3284612 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19