Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.4350. Min Act: -0.1700
Data Index: 2653626 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.4350. Min Act: -0.1700
Data Index: 5030449 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.4350. Min Act: -0.1700
Data Index: 2056144 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.4350. Min Act: -0.1700
Data Index: 6878082 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.4038. Min Act: -0.1700
Data Index: 6480466 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.3725. Min Act: -0.1700
Data Index: 6285694 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.3413. Min Act: -0.1700
Data Index: 8539237 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.3100. Min Act: -0.1700
Data Index: 5150881 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.3100. Min Act: -0.1700
Data Index: 3262247 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.2475. Min Act: -0.1700
Data Index: 7815533 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.2163. Min Act: -0.1700
Data Index: 5961347 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.2163. Min Act: -0.1700
Data Index: 1526823 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1850. Min Act: -0.1700
Data Index: 6946705 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1538. Min Act: -0.1700
Data Index: 317072 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1538. Min Act: -0.1700
Data Index: 957056 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1538. Min Act: -0.1700
Data Index: 7449332 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1538. Min Act: -0.1700
Data Index: 7535295 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1538. Min Act: -0.1700
Data Index: 1510395 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1225. Min Act: -0.1700
Data Index: 5861598 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4350. Min Range: -6.4350
Max Act: 6.1225. Min Act: -0.1700
Data Index: 3988410 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19