Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.3601. Min Act: -0.1700
Data Index: 5422144 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.3288. Min Act: -0.1700
Data Index: 4146622 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.2038. Min Act: -0.1700
Data Index: 4644087 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.1413. Min Act: -0.1700
Data Index: 5489039 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.0163. Min Act: -0.1700
Data Index: 7151812 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.0163. Min Act: -0.1700
Data Index: 7208520 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3601. Min Range: -6.3601
Max Act: 6.0163. Min Act: -0.1700
Data Index: 7442637 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8913. Min Act: -0.1700
Data Index: 543127 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8913. Min Act: -0.1700
Data Index: 5990555 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.9226. Min Act: -0.1700
Data Index: 8120924 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.9226. Min Act: -0.1700
Data Index: 3072618 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3757434 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8913. Min Act: -0.1700
Data Index: 7442639 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8601. Min Act: -0.1700
Data Index: 1870883 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8288. Min Act: -0.1700
Data Index: 1554169 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8288. Min Act: -0.1700
Data Index: 8305339 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8601. Min Act: -0.1700
Data Index: 939122 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8288. Min Act: -0.1700
Data Index: 3788624 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8288. Min Act: -0.1700
Data Index: 5687608 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3601. Min Range: -6.3601
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4493389 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19