Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.6545. Min Act: -0.1700
Data Index: 4639349 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.6545. Min Act: -0.1700
Data Index: 385628 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.5920. Min Act: -0.1700
Data Index: 7073086 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.5920. Min Act: -0.1700
Data Index: 5608029 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.4983. Min Act: -0.1700
Data Index: 1732366 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.4358. Min Act: -0.1700
Data Index: 2664993 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.2170. Min Act: -0.1700
Data Index: 5238062 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.2170. Min Act: -0.1700
Data Index: 4515476 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1858. Min Act: -0.1700
Data Index: 8087005 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1858. Min Act: -0.1700
Data Index: 514693 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1545. Min Act: -0.1700
Data Index: 3933228 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1858. Min Act: -0.1700
Data Index: 2378976 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1545. Min Act: -0.1700
Data Index: 8679487 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1545. Min Act: -0.1700
Data Index: 1726193 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1545. Min Act: -0.1700
Data Index: 3287491 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1233. Min Act: -0.1700
Data Index: 6719112 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.1233. Min Act: -0.1700
Data Index: 4362282 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.0920. Min Act: -0.1700
Data Index: 232345 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.0920. Min Act: -0.1700
Data Index: 4065 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6545. Min Range: -7.6545
Max Act: 7.0608. Min Act: -0.1700
Data Index: 270966 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19