Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7200. Min Range: -8.7200
Max Act: 8.7200. Min Act: -0.1700
Data Index: 4143889 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7200. Min Range: -8.7200
Max Act: 8.7200. Min Act: -0.1700
Data Index: 7174558 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.8762. Min Act: -0.1700
Data Index: 7359087 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.8762. Min Act: -0.1700
Data Index: 7909953 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.8762. Min Act: -0.1700
Data Index: 412336 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.8762. Min Act: -0.1700
Data Index: 3017212 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.7825. Min Act: -0.1700
Data Index: 4390349 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.8137. Min Act: -0.1700
Data Index: 674026 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.7200. Min Act: -0.1700
Data Index: 1437157 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.6887. Min Act: -0.1700
Data Index: 4974210 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.6887. Min Act: -0.1700
Data Index: 3561106 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.6575. Min Act: -0.1700
Data Index: 8807129 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.6262. Min Act: -0.1700
Data Index: 6781773 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.6575. Min Act: -0.1700
Data Index: 8082172 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 4044949 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 5694568 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.5637. Min Act: -0.1700
Data Index: 3406271 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.5637. Min Act: -0.1700
Data Index: 813195 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 4057592 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7200. Min Range: -8.7200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 7713107 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19