Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1958271 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.3398. Min Act: -0.1700
Data Index: 860603 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.3086. Min Act: -0.1700
Data Index: 2995811 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1836. Min Act: -0.1700
Data Index: 3594729 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.2148. Min Act: -0.1700
Data Index: 6888352 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.2148. Min Act: -0.1700
Data Index: 6933971 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1836. Min Act: -0.1700
Data Index: 120938 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1836. Min Act: -0.1700
Data Index: 724561 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1523. Min Act: -0.1700
Data Index: 3706018 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1523. Min Act: -0.1700
Data Index: 1383681 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.1211. Min Act: -0.1700
Data Index: 5303878 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.0586. Min Act: -0.1700
Data Index: 4529453 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.0273. Min Act: -0.1700
Data Index: 6133219 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.0273. Min Act: -0.1700
Data Index: 2787018 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.0273. Min Act: -0.1700
Data Index: 80636 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.0586. Min Act: -0.1700
Data Index: 864455 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6211. Min Range: -5.6211
Max Act: 4.9961. Min Act: -0.1700
Data Index: 7188816 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6211. Min Range: -5.6211
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1226922 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6211. Min Range: -5.6211
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1803181 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6211. Min Range: -5.6211
Max Act: 4.9961. Min Act: -0.1700
Data Index: 7878680 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19