Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.5277. Min Act: -0.1700
Data Index: 6030477 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.4027. Min Act: -0.1700
Data Index: 5984368 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3402. Min Act: -0.1700
Data Index: 5175622 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.3090. Min Act: -0.1700
Data Index: 8135759 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2465. Min Act: -0.1700
Data Index: 5480779 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2777. Min Act: -0.1700
Data Index: 5649195 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2465. Min Act: -0.1700
Data Index: 6897199 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2465. Min Act: -0.1700
Data Index: 8808057 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2152. Min Act: -0.1700
Data Index: 7523531 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2152. Min Act: -0.1700
Data Index: 7858687 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2152. Min Act: -0.1700
Data Index: 3771047 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.2152. Min Act: -0.1700
Data Index: 517116 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1751758 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1527. Min Act: -0.1700
Data Index: 122392 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1527. Min Act: -0.1700
Data Index: 3754043 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1527. Min Act: -0.1700
Data Index: 3828809 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1840. Min Act: -0.1700
Data Index: 8596079 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1215. Min Act: -0.1700
Data Index: 478805 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6971046 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5277. Min Range: -5.5277
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6690066 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19