Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.7424. Min Act: -0.1700
Data Index: 3999183 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.5549. Min Act: -0.1700
Data Index: 5766228 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.5549. Min Act: -0.1700
Data Index: 5409852 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.4924. Min Act: -0.1700
Data Index: 8310928 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.4924. Min Act: -0.1700
Data Index: 3427170 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.4299. Min Act: -0.1700
Data Index: 4355888 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.3674. Min Act: -0.1700
Data Index: 8082158 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.3674. Min Act: -0.1700
Data Index: 2749007 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.3049. Min Act: -0.1700
Data Index: 4834956 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.3049. Min Act: -0.1700
Data Index: 3483886 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.2424. Min Act: -0.1700
Data Index: 867042 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.2424. Min Act: -0.1700
Data Index: 1419036 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1799. Min Act: -0.1700
Data Index: 3953952 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1799. Min Act: -0.1700
Data Index: 6325721 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1799. Min Act: -0.1700
Data Index: 8110230 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1799. Min Act: -0.1700
Data Index: 2145555 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4912387 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.0549. Min Act: -0.1700
Data Index: 1008729 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1174. Min Act: -0.1700
Data Index: 4312212 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7424. Min Range: -8.7424
Max Act: 8.1174. Min Act: -0.1700
Data Index: 2140563 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19