Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.7489. Min Act: -0.1700
Data Index: 1610678 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.5927. Min Act: -0.1700
Data Index: 2934536 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.5614. Min Act: -0.1700
Data Index: 8326139 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.5302. Min Act: -0.1700
Data Index: 1141427 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4364. Min Act: -0.1700
Data Index: 8793143 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4364. Min Act: -0.1700
Data Index: 3934412 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4364. Min Act: -0.1700
Data Index: 7796046 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3739. Min Act: -0.1700
Data Index: 5598986 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4052. Min Act: -0.1700
Data Index: 8065638 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4052. Min Act: -0.1700
Data Index: 1150110 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.4364. Min Act: -0.1700
Data Index: 7006069 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3427. Min Act: -0.1700
Data Index: 2472126 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3427. Min Act: -0.1700
Data Index: 2273997 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3114. Min Act: -0.1700
Data Index: 4431214 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2437141 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3114. Min Act: -0.1700
Data Index: 1731059 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3114. Min Act: -0.1700
Data Index: 470496 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.3114. Min Act: -0.1700
Data Index: 6400561 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.2802. Min Act: -0.1700
Data Index: 2583502 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7489. Min Range: -5.7489
Max Act: 5.2802. Min Act: -0.1700
Data Index: 6231506 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19