Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5692 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 5860041 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 8720243 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.3038. Min Act: -0.1700
Data Index: 7071538 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.1163. Min Act: -0.1700
Data Index: 8593601 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.0538. Min Act: -0.1700
Data Index: 2964301 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.0226. Min Act: -0.1700
Data Index: 5025667 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3038. Min Range: -6.3038
Max Act: 6.0226. Min Act: -0.1700
Data Index: 4243936 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.9601. Min Act: -0.1700
Data Index: 7244004 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8976. Min Act: -0.1700
Data Index: 723519 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8663. Min Act: -0.1700
Data Index: 1504512 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8663. Min Act: -0.1700
Data Index: 6099752 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8663. Min Act: -0.1700
Data Index: 8389080 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7012125 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8351. Min Act: -0.1700
Data Index: 5055322 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8351. Min Act: -0.1700
Data Index: 2885994 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 6140997 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 5629603 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 1910797 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 1481707 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3038. Min Range: -6.3038
Max Act: 5.7726. Min Act: -0.1700
Data Index: 4169369 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19