Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.5484. Min Act: -0.1700
Data Index: 5069461 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.4546. Min Act: -0.1700
Data Index: 2059034 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3921. Min Act: -0.1700
Data Index: 8730442 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3921. Min Act: -0.1700
Data Index: 2708899 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3609. Min Act: -0.1700
Data Index: 5843157 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3609. Min Act: -0.1700
Data Index: 3800819 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3609. Min Act: -0.1700
Data Index: 6062785 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3609. Min Act: -0.1700
Data Index: 165649 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3609. Min Act: -0.1700
Data Index: 911283 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3296. Min Act: -0.1700
Data Index: 8800711 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.3296. Min Act: -0.1700
Data Index: 687933 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2983. Min Act: -0.1700
Data Index: 8318810 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2671. Min Act: -0.1700
Data Index: 7070724 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2671. Min Act: -0.1700
Data Index: 860771 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2671. Min Act: -0.1700
Data Index: 6790242 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2671. Min Act: -0.1700
Data Index: 2330395 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2671. Min Act: -0.1700
Data Index: 5622027 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2358. Min Act: -0.1700
Data Index: 6141588 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2358. Min Act: -0.1700
Data Index: 2385278 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5484. Min Range: -4.5484
Max Act: 4.2358. Min Act: -0.1700
Data Index: 3909656 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19