Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0470. Min Range: -7.0470
Max Act: 7.0470. Min Act: -0.1700
Data Index: 3588078 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.9532. Min Act: -0.1700
Data Index: 4696526 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.7970. Min Act: -0.1700
Data Index: 2492207 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.7657. Min Act: -0.1700
Data Index: 882603 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.7032. Min Act: -0.1700
Data Index: 8698877 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.7032. Min Act: -0.1700
Data Index: 4409076 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.6720. Min Act: -0.1700
Data Index: 7196449 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.6407. Min Act: -0.1700
Data Index: 5015668 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.6095. Min Act: -0.1700
Data Index: 5645359 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.6095. Min Act: -0.1700
Data Index: 2875066 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5782. Min Act: -0.1700
Data Index: 868712 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5782. Min Act: -0.1700
Data Index: 8314221 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.6095. Min Act: -0.1700
Data Index: 973359 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 4339574 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 5728852 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 2296050 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 786555 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 8046624 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5470. Min Act: -0.1700
Data Index: 6331846 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0470. Min Range: -7.0470
Max Act: 6.5157. Min Act: -0.1700
Data Index: 2667112 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19