Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.3370. Min Act: -0.1700
Data Index: 6012542 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.3370. Min Act: -0.1700
Data Index: 26146 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.2120. Min Act: -0.1700
Data Index: 7572506 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.2120. Min Act: -0.1700
Data Index: 174438 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0870. Min Act: -0.1700
Data Index: 4739062 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 5474914 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 8581605 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 459900 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 5730406 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 3236388 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.9620. Min Act: -0.1700
Data Index: 7875616 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3370. Min Range: -9.3370
Max Act: 9.0245. Min Act: -0.1700
Data Index: 5655383 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.9620. Min Act: -0.1700
Data Index: 1199985 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8995. Min Act: -0.1700
Data Index: 5062240 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8995. Min Act: -0.1700
Data Index: 4685697 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.9620. Min Act: -0.1700
Data Index: 4665803 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8370. Min Act: -0.1700
Data Index: 1951572 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8995. Min Act: -0.1700
Data Index: 6512163 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8370. Min Act: -0.1700
Data Index: 8694051 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3370. Min Range: -9.3370
Max Act: 8.8995. Min Act: -0.1700
Data Index: 6451188 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19