Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.5351. Min Act: -0.1700
Data Index: 6612608 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.3476. Min Act: -0.1700
Data Index: 6760825 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.2851. Min Act: -0.1700
Data Index: 3242277 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.2851. Min Act: -0.1700
Data Index: 4699546 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.2226. Min Act: -0.1700
Data Index: 7162054 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.0976. Min Act: -0.1700
Data Index: 1089480 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.0976. Min Act: -0.1700
Data Index: 8059395 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.0976. Min Act: -0.1700
Data Index: 1900025 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.0351. Min Act: -0.1700
Data Index: 348557 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5351. Min Range: -8.5351
Max Act: 8.0351. Min Act: -0.1700
Data Index: 2688219 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 6000883 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 3873424 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 5573358 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9101. Min Act: -0.1700
Data Index: 6468970 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 975128 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 8522235 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 6900636 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9726. Min Act: -0.1700
Data Index: 3212715 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9101. Min Act: -0.1700
Data Index: 3390248 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5351. Min Range: -8.5351
Max Act: 7.9101. Min Act: -0.1700
Data Index: 3704460 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19