Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.4233. Min Act: -0.1700
Data Index: 3417010 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.4077. Min Act: -0.1700
Data Index: 7812259 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.3292. Min Act: -0.1700
Data Index: 3641517 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.3292. Min Act: -0.1700
Data Index: 6292000 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.3136. Min Act: -0.1700
Data Index: 2056243 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2822. Min Act: -0.1700
Data Index: 2631120 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2979. Min Act: -0.1700
Data Index: 4091833 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2822. Min Act: -0.1700
Data Index: 2543944 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2665. Min Act: -0.1700
Data Index: 2160988 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2822. Min Act: -0.1700
Data Index: 7247087 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2507. Min Act: -0.1700
Data Index: 7969146 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2193. Min Act: -0.1700
Data Index: 8769448 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2036. Min Act: -0.1700
Data Index: 8365732 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2507. Min Act: -0.1700
Data Index: 302077 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.1879. Min Act: -0.1700
Data Index: 111773 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2193. Min Act: -0.1700
Data Index: 5133048 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2036. Min Act: -0.1700
Data Index: 6218160 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2036. Min Act: -0.1700
Data Index: 7467532 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2193. Min Act: -0.1700
Data Index: 1023511 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4233. Min Range: -3.4233
Max Act: 3.2036. Min Act: -0.1700
Data Index: 6703766 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19