Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1248. Min Range: -8.1248
Max Act: 8.1248. Min Act: -0.1700
Data Index: 8495464 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.9373. Min Act: -0.1700
Data Index: 4704865 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.8123. Min Act: -0.1700
Data Index: 8253174 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.7498. Min Act: -0.1700
Data Index: 5346314 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.7498. Min Act: -0.1700
Data Index: 8649333 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.7498. Min Act: -0.1700
Data Index: 3595240 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.6248. Min Act: -0.1700
Data Index: 6076534 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.5936. Min Act: -0.1700
Data Index: 4343711 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.5936. Min Act: -0.1700
Data Index: 4360649 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.5623. Min Act: -0.1700
Data Index: 7103128 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.5623. Min Act: -0.1700
Data Index: 81294 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.4998. Min Act: -0.1700
Data Index: 7074479 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.4686. Min Act: -0.1700
Data Index: 5815743 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.4373. Min Act: -0.1700
Data Index: 6085479 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3748. Min Act: -0.1700
Data Index: 988654 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3123. Min Act: -0.1700
Data Index: 2224831 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3123. Min Act: -0.1700
Data Index: 4569978 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3436. Min Act: -0.1700
Data Index: 3164413 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3123. Min Act: -0.1700
Data Index: 6131293 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1248. Min Range: -8.1248
Max Act: 7.3123. Min Act: -0.1700
Data Index: 6131301 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19