Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6111 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1623. Min Act: -0.1700
Data Index: 1727183 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1623. Min Range: -4.1623
Max Act: 4.1623. Min Act: -0.1700
Data Index: 6884704 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.9435. Min Act: -0.1700
Data Index: 5269483 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.8810. Min Act: -0.1700
Data Index: 5619828 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.8340. Min Act: -0.1700
Data Index: 666958 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.7715. Min Act: -0.1700
Data Index: 6820832 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.7715. Min Act: -0.1700
Data Index: 759342 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.7402. Min Act: -0.1700
Data Index: 5970692 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.7246. Min Act: -0.1700
Data Index: 727163 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6933. Min Act: -0.1700
Data Index: 5947273 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6777. Min Act: -0.1700
Data Index: 6124023 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6777. Min Act: -0.1700
Data Index: 7595401 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6777. Min Act: -0.1700
Data Index: 887837 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6777. Min Act: -0.1700
Data Index: 3349647 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6464. Min Act: -0.1700
Data Index: 3483134 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6620. Min Act: -0.1700
Data Index: 3203680 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6307. Min Act: -0.1700
Data Index: 5577418 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6464. Min Act: -0.1700
Data Index: 5374894 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6307. Min Act: -0.1700
Data Index: 4874391 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1623. Min Range: -4.1623
Max Act: 3.6464. Min Act: -0.1700
Data Index: 3566602 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19