Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.8513. Min Act: -0.1700
Data Index: 3720134 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5701. Min Act: -0.1700
Data Index: 8466410 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.5388. Min Act: -0.1700
Data Index: 6185847 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.4451. Min Act: -0.1700
Data Index: 822209 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.3826. Min Act: -0.1700
Data Index: 2547394 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.3826. Min Act: -0.1700
Data Index: 3349291 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.3513. Min Act: -0.1700
Data Index: 1708424 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.3513. Min Act: -0.1700
Data Index: 2681792 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.3201. Min Act: -0.1700
Data Index: 2278229 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2888. Min Act: -0.1700
Data Index: 1708435 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2888. Min Act: -0.1700
Data Index: 1748939 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2888. Min Act: -0.1700
Data Index: 6865200 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2888. Min Act: -0.1700
Data Index: 1708439 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2575. Min Act: -0.1700
Data Index: 221564 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2575. Min Act: -0.1700
Data Index: 5658824 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2888. Min Act: -0.1700
Data Index: 6410843 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2575. Min Act: -0.1700
Data Index: 5250111 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2263. Min Act: -0.1700
Data Index: 7149001 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1708427 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8513. Min Range: -4.8513
Max Act: 4.2263. Min Act: -0.1700
Data Index: 5072434 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19