Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.6570. Min Act: -0.1700
Data Index: 6277147 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.6257. Min Act: -0.1700
Data Index: 4500969 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.5320. Min Act: -0.1700
Data Index: 5636328 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.5007. Min Act: -0.1700
Data Index: 3384475 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4695. Min Act: -0.1700
Data Index: 6244792 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4695. Min Act: -0.1700
Data Index: 7019574 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4382. Min Act: -0.1700
Data Index: 1346972 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 6667654 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 3485486 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 7003224 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4382. Min Act: -0.1700
Data Index: 4279371 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 8292835 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 1750582 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3757. Min Act: -0.1700
Data Index: 256521 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3757. Min Act: -0.1700
Data Index: 3408219 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.4069. Min Act: -0.1700
Data Index: 1920157 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3444. Min Act: -0.1700
Data Index: 6101381 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3444. Min Act: -0.1700
Data Index: 4198964 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3444. Min Act: -0.1700
Data Index: 2825684 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6570. Min Range: -4.6570
Max Act: 4.3444. Min Act: -0.1700
Data Index: 472998 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19