Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.7443. Min Act: -0.1700
Data Index: 8613395 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.6818. Min Act: -0.1700
Data Index: 1848878 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.6505. Min Act: -0.1700
Data Index: 231582 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.5880. Min Act: -0.1700
Data Index: 715277 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.5568. Min Act: -0.1700
Data Index: 5056503 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.5568. Min Act: -0.1700
Data Index: 4820076 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4943. Min Act: -0.1700
Data Index: 3377513 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4943. Min Act: -0.1700
Data Index: 8325190 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4630. Min Act: -0.1700
Data Index: 643258 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4318. Min Act: -0.1700
Data Index: 6688919 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4318. Min Act: -0.1700
Data Index: 599912 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4318. Min Act: -0.1700
Data Index: 8078773 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4005. Min Act: -0.1700
Data Index: 6937348 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.4005. Min Act: -0.1700
Data Index: 1962964 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3380. Min Act: -0.1700
Data Index: 995884 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3693. Min Act: -0.1700
Data Index: 8576259 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3693. Min Act: -0.1700
Data Index: 6171905 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3380. Min Act: -0.1700
Data Index: 8099453 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3380. Min Act: -0.1700
Data Index: 8107364 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7443. Min Range: -5.7443
Max Act: 5.3380. Min Act: -0.1700
Data Index: 4594153 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19