Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 403 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.2726. Min Act: -0.1700
Data Index: 5164536 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.2101. Min Act: -0.1700
Data Index: 3492102 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.0851. Min Act: -0.1700
Data Index: 5676835 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.0851. Min Act: -0.1700
Data Index: 2317752 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.0226. Min Act: -0.1700
Data Index: 8672309 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.9601. Min Act: -0.1700
Data Index: 5606945 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2726. Min Range: -9.2726
Max Act: 9.0226. Min Act: -0.1700
Data Index: 3618400 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8351. Min Act: -0.1700
Data Index: 4921259 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8976. Min Act: -0.1700
Data Index: 5087377 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8351. Min Act: -0.1700
Data Index: 8456552 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8351. Min Act: -0.1700
Data Index: 779943 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8351. Min Act: -0.1700
Data Index: 1924040 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.8351. Min Act: -0.1700
Data Index: 779944 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7726. Min Act: -0.1700
Data Index: 197968 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7726. Min Act: -0.1700
Data Index: 8609286 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7726. Min Act: -0.1700
Data Index: 6878275 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7726. Min Act: -0.1700
Data Index: 8633164 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7726. Min Act: -0.1699
Data Index: 8563326 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7101. Min Act: -0.1700
Data Index: 5575499 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2726. Min Range: -9.2726
Max Act: 8.7101. Min Act: -0.1700
Data Index: 6160854 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19