Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2851. Min Range: -8.2851
Max Act: 8.2851. Min Act: -0.1700
Data Index: 2013177 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.9101. Min Act: -0.1700
Data Index: 5894864 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.8476. Min Act: -0.1700
Data Index: 6173 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.8476. Min Act: -0.1700
Data Index: 6925112 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.8476. Min Act: -0.1700
Data Index: 6561379 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.7226. Min Act: -0.1700
Data Index: 7407789 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.7226. Min Act: -0.1700
Data Index: 2658409 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.6601. Min Act: -0.1700
Data Index: 6598134 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.5976. Min Act: -0.1700
Data Index: 6005428 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.5976. Min Act: -0.1700
Data Index: 6632528 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.5663. Min Act: -0.1700
Data Index: 6694261 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.5351. Min Act: -0.1700
Data Index: 1133269 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.5038. Min Act: -0.1700
Data Index: 8648450 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4726. Min Act: -0.1700
Data Index: 7079093 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4726. Min Act: -0.1700
Data Index: 293320 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4413. Min Act: -0.1700
Data Index: 7053036 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4413. Min Act: -0.1700
Data Index: 5542225 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4413. Min Act: -0.1700
Data Index: 5044464 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4101. Min Act: -0.1700
Data Index: 601423 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2851. Min Range: -8.2851
Max Act: 7.4101. Min Act: -0.1700
Data Index: 1212173 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19