Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0335. Min Range: -7.0335
Max Act: 7.0335. Min Act: -0.1700
Data Index: 4599755 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.9397. Min Act: -0.1700
Data Index: 6950954 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.7522. Min Act: -0.1700
Data Index: 8372896 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.7210. Min Act: -0.1700
Data Index: 1302950 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6585. Min Act: -0.1700
Data Index: 3289339 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5960. Min Act: -0.1700
Data Index: 144609 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6897. Min Act: -0.1700
Data Index: 3947545 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6585. Min Act: -0.1700
Data Index: 3945102 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6272. Min Act: -0.1700
Data Index: 7863425 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6585. Min Act: -0.1700
Data Index: 5354373 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6272. Min Act: -0.1700
Data Index: 3971700 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5960. Min Act: -0.1700
Data Index: 456101 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5960. Min Act: -0.1700
Data Index: 5927249 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5960. Min Act: -0.1700
Data Index: 48862 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.6272. Min Act: -0.1700
Data Index: 7945400 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5647. Min Act: -0.1700
Data Index: 6543299 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5647. Min Act: -0.1700
Data Index: 864238 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5647. Min Act: -0.1700
Data Index: 3606538 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5647. Min Act: -0.1700
Data Index: 3239097 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0335. Min Range: -7.0335
Max Act: 6.5335. Min Act: -0.1700
Data Index: 5486589 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19