Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.8547. Min Act: -0.1700
Data Index: 211015 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.6360. Min Act: -0.1700
Data Index: 3492914 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.5735. Min Act: -0.1700
Data Index: 8419111 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.5422. Min Act: -0.1700
Data Index: 7911669 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.5422. Min Act: -0.1700
Data Index: 1133352 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.4485. Min Act: -0.1700
Data Index: 5475893 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.4485. Min Act: -0.1700
Data Index: 4855921 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.4172. Min Act: -0.1700
Data Index: 1010602 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.3860. Min Act: -0.1700
Data Index: 2355158 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.3235. Min Act: -0.1700
Data Index: 1019016 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.3235. Min Act: -0.1700
Data Index: 1968955 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2922. Min Act: -0.1700
Data Index: 3683235 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2610. Min Act: -0.1700
Data Index: 7290662 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2922. Min Act: -0.1700
Data Index: 8539480 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2297. Min Act: -0.1700
Data Index: 2728614 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2610. Min Act: -0.1700
Data Index: 6291745 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2610. Min Act: -0.1700
Data Index: 2963057 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2297. Min Act: -0.1700
Data Index: 7735890 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2297. Min Act: -0.1700
Data Index: 7596793 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8547. Min Range: -6.8547
Max Act: 6.2297. Min Act: -0.1700
Data Index: 6754859 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19