Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.3747. Min Act: -0.1700
Data Index: 5679420 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.2184. Min Act: -0.1700
Data Index: 996079 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.2497. Min Act: -0.1700
Data Index: 7618736 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.0622. Min Act: -0.1700
Data Index: 3020701 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.0622. Min Act: -0.1700
Data Index: 1705835 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.0622. Min Act: -0.1700
Data Index: 5679416 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.0309. Min Act: -0.1700
Data Index: 592316 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3747. Min Range: -7.3747
Max Act: 7.0309. Min Act: -0.1700
Data Index: 3069790 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9997. Min Act: -0.1700
Data Index: 5679414 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9684. Min Act: -0.1700
Data Index: 8489007 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9372. Min Act: -0.1700
Data Index: 4733039 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9059. Min Act: -0.1700
Data Index: 3176709 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9059. Min Act: -0.1700
Data Index: 4466258 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.9059. Min Act: -0.1700
Data Index: 1195595 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.8747. Min Act: -0.1700
Data Index: 6661710 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.8434. Min Act: -0.1700
Data Index: 5213394 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7809. Min Act: -0.1700
Data Index: 6132547 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7809. Min Act: -0.1700
Data Index: 766368 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7497. Min Act: -0.1700
Data Index: 5497492 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3747. Min Range: -7.3747
Max Act: 6.7497. Min Act: -0.1700
Data Index: 1619441 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19