Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1330. Min Range: -6.1330
Max Act: 6.1330. Min Act: -0.1700
Data Index: 5054455 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.6643. Min Act: -0.1700
Data Index: 8662382 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.6330. Min Act: -0.1700
Data Index: 5854725 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.5705. Min Act: -0.1700
Data Index: 4223005 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.5393. Min Act: -0.1700
Data Index: 3217395 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.5080. Min Act: -0.1700
Data Index: 7803130 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4768. Min Act: -0.1700
Data Index: 6653941 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4768. Min Act: -0.1700
Data Index: 8585926 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.5080. Min Act: -0.1700
Data Index: 1361268 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.5080. Min Act: -0.1700
Data Index: 391428 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4455. Min Act: -0.1700
Data Index: 2302104 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4768. Min Act: -0.1700
Data Index: 568174 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4768. Min Act: -0.1700
Data Index: 6873697 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4143. Min Act: -0.1700
Data Index: 6560958 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4143. Min Act: -0.1700
Data Index: 6955632 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.4143. Min Act: -0.1700
Data Index: 6825096 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.3830. Min Act: -0.1700
Data Index: 360585 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.3518. Min Act: -0.1700
Data Index: 6455754 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.3830. Min Act: -0.1700
Data Index: 3225196 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1330. Min Range: -6.1330
Max Act: 5.3830. Min Act: -0.1700
Data Index: 5591342 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19