Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2131 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.6401. Min Act: -0.1700
Data Index: 3179800 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 409377 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 3179798 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.3276. Min Act: -0.1700
Data Index: 8728144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.3589. Min Act: -0.1700
Data Index: 1484473 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2964. Min Act: -0.1700
Data Index: 2363080 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.3276. Min Act: -0.1700
Data Index: 6424445 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2964. Min Act: -0.1700
Data Index: 771474 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2651. Min Act: -0.1700
Data Index: 2090821 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2651. Min Act: -0.1700
Data Index: 3655434 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2651. Min Act: -0.1700
Data Index: 3655436 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2339. Min Act: -0.1700
Data Index: 4115991 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2651. Min Act: -0.1700
Data Index: 2838151 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2339. Min Act: -0.1700
Data Index: 4157244 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2339. Min Act: -0.1700
Data Index: 2404166 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2026. Min Act: -0.1700
Data Index: 4864426 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2026. Min Act: -0.1700
Data Index: 1121695 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2026. Min Act: -0.1700
Data Index: 3179799 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2026. Min Act: -0.1700
Data Index: 6604132 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.2026. Min Act: -0.1700
Data Index: 7547541 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19