Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.1103. Min Act: -0.1700
Data Index: 5549925 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0767. Min Act: -0.1700
Data Index: 5518146 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0767. Min Act: -0.1700
Data Index: 1006601 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0935. Min Act: -0.1700
Data Index: 1518128 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0767. Min Act: -0.1700
Data Index: 2871881 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0767. Min Act: -0.1700
Data Index: 3694130 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 3741174 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 2479499 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 1196149 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0600. Min Act: -0.1700
Data Index: 4652740 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 7656761 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 8623453 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0431. Min Act: -0.1700
Data Index: 1236105 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 218679 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 8654115 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 8588222 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 7995206 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 1099186 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0094. Min Act: -0.1700
Data Index: 6782302 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1103. Min Range: -2.1103
Max Act: 2.0263. Min Act: -0.1700
Data Index: 460214 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19