Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.6876. Min Act: -0.1700
Data Index: 3524421 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.6251. Min Act: -0.1700
Data Index: 8098970 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5938. Min Act: -0.1700
Data Index: 7055221 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5001. Min Act: -0.1700
Data Index: 2030814 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5313. Min Act: -0.1700
Data Index: 6725038 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5313. Min Act: -0.1700
Data Index: 3740960 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5313. Min Act: -0.1700
Data Index: 2030803 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5001. Min Act: -0.1700
Data Index: 924769 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.5001. Min Act: -0.1700
Data Index: 2710301 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4376. Min Act: -0.1700
Data Index: 8706567 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4688. Min Act: -0.1700
Data Index: 847162 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4801441 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4376. Min Act: -0.1700
Data Index: 2468404 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4376. Min Act: -0.1700
Data Index: 3317684 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4376. Min Act: -0.1700
Data Index: 306602 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4376. Min Act: -0.1700
Data Index: 6977712 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4063. Min Act: -0.1700
Data Index: 5375036 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4063. Min Act: -0.1700
Data Index: 6566911 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.4063. Min Act: -0.1700
Data Index: 6074928 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6876. Min Range: -5.6876
Max Act: 5.3438. Min Act: -0.1700
Data Index: 6407848 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19