Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3840. Min Act: -0.1700
Data Index: 1956852 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3840. Min Act: -0.1700
Data Index: 7632122 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3527. Min Act: -0.1700
Data Index: 8823593 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3215. Min Act: -0.1700
Data Index: 6743333 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3527. Min Act: -0.1700
Data Index: 5053759 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3215. Min Act: -0.1700
Data Index: 8815396 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.3215. Min Act: -0.1700
Data Index: 7951393 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.2590. Min Act: -0.1700
Data Index: 2204604 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.2277. Min Act: -0.1700
Data Index: 7661935 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.2277. Min Act: -0.1700
Data Index: 6675036 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1965. Min Act: -0.1700
Data Index: 6029975 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1965. Min Act: -0.1700
Data Index: 4201207 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1652. Min Act: -0.1700
Data Index: 1998467 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1652. Min Act: -0.1700
Data Index: 1308506 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1965. Min Act: -0.1700
Data Index: 497076 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1652. Min Act: -0.1700
Data Index: 7003985 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1340. Min Act: -0.1700
Data Index: 2936852 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1652. Min Act: -0.1700
Data Index: 7779151 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1027. Min Act: -0.1700
Data Index: 3608137 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3840. Min Range: -5.3840
Max Act: 5.1340. Min Act: -0.1700
Data Index: 4407367 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19