Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.5522. Min Act: -0.1700
Data Index: 3751164 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.5522. Min Act: -0.1700
Data Index: 6030583 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.5522. Min Act: -0.1700
Data Index: 5930132 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.5209. Min Act: -0.1700
Data Index: 4990801 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.4897. Min Act: -0.1700
Data Index: 6867799 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.4584. Min Act: -0.1700
Data Index: 5164754 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.4272. Min Act: -0.1700
Data Index: 3218295 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.4272. Min Act: -0.1700
Data Index: 1763437 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3959. Min Act: -0.1700
Data Index: 3924126 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3959. Min Act: -0.1700
Data Index: 1763438 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3647. Min Act: -0.1700
Data Index: 1763436 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 2093178 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3647. Min Act: -0.1700
Data Index: 7833074 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 2888680 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 1223415 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 304142 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 6161988 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3334. Min Act: -0.1700
Data Index: 1557275 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3647. Min Act: -0.1700
Data Index: 1763435 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5522. Min Range: -4.5522
Max Act: 4.3022. Min Act: -0.1700
Data Index: 799710 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19