Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0231. Min Range: -7.0231
Max Act: 7.0231. Min Act: -0.1700
Data Index: 545575 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.7731. Min Act: -0.1700
Data Index: 2908274 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.7419. Min Act: -0.1700
Data Index: 4424377 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.7419. Min Act: -0.1700
Data Index: 5735722 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.6169. Min Act: -0.1700
Data Index: 4636106 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.6169. Min Act: -0.1700
Data Index: 4134696 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.5856. Min Act: -0.1700
Data Index: 8694651 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.5544. Min Act: -0.1700
Data Index: 3940678 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.5231. Min Act: -0.1700
Data Index: 4251379 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.5231. Min Act: -0.1700
Data Index: 7492513 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.4606. Min Act: -0.1700
Data Index: 1171658 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.4606. Min Act: -0.1700
Data Index: 1335809 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.4919. Min Act: -0.1700
Data Index: 643059 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.4294. Min Act: -0.1700
Data Index: 199834 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.4294. Min Act: -0.1700
Data Index: 2908476 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.3669. Min Act: -0.1700
Data Index: 6743667 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.3981. Min Act: -0.1700
Data Index: 3496301 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.3981. Min Act: -0.1700
Data Index: 1055554 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.3356. Min Act: -0.1700
Data Index: 6688893 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0231. Min Range: -7.0231
Max Act: 6.3356. Min Act: -0.1700
Data Index: 6212811 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19