Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2472. Min Act: -0.1700
Data Index: 5938001 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8651523 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1847. Min Act: -0.1700
Data Index: 3058417 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8695607 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8566735 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1847. Min Act: -0.1700
Data Index: 1999979 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8715198 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1847. Min Act: -0.1700
Data Index: 6708164 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1847. Min Act: -0.1700
Data Index: 8299485 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 2706336 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 3626004 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 2600583 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 4263087 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 1694895 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1535. Min Act: -0.1700
Data Index: 8048413 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8059071 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1222. Min Act: -0.1700
Data Index: 4112309 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1222. Min Act: -0.1700
Data Index: 3842545 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.1222. Min Act: -0.1700
Data Index: 5555880 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.0910. Min Act: -0.1700
Data Index: 3097337 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19