Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1206. Min Range: -7.1206
Max Act: 7.1206. Min Act: -0.1700
Data Index: 3334796 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.9956. Min Act: -0.1700
Data Index: 4404342 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.9018. Min Act: -0.1700
Data Index: 2052371 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.7143. Min Act: -0.1700
Data Index: 2163973 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.7143. Min Act: -0.1700
Data Index: 1304068 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.6518. Min Act: -0.1700
Data Index: 6370818 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.5581. Min Act: -0.1700
Data Index: 6678904 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.5581. Min Act: -0.1700
Data Index: 8667290 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.5581. Min Act: -0.1700
Data Index: 7491995 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4956. Min Act: -0.1700
Data Index: 6158442 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4643. Min Act: -0.1700
Data Index: 4087144 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4956. Min Act: -0.1700
Data Index: 3108936 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4643. Min Act: -0.1700
Data Index: 1029250 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3153754 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4956. Min Act: -0.1700
Data Index: 2122700 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4331. Min Act: -0.1700
Data Index: 7503842 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4331. Min Act: -0.1700
Data Index: 8017869 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.4018. Min Act: -0.1700
Data Index: 894312 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.3706. Min Act: -0.1700
Data Index: 7624665 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1206. Min Range: -7.1206
Max Act: 6.3393. Min Act: -0.1700
Data Index: 1345412 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19