Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.6194. Min Act: -0.1700
Data Index: 3020005 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.5569. Min Act: -0.1700
Data Index: 4121511 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.4319. Min Act: -0.1700
Data Index: 1851705 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.4319. Min Act: -0.1700
Data Index: 7645920 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.3694. Min Act: -0.1700
Data Index: 7307526 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.3069. Min Act: -0.1700
Data Index: 711377 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.2444. Min Act: -0.1700
Data Index: 617231 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.2444. Min Act: -0.1700
Data Index: 3091694 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 2578428 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.2444. Min Act: -0.1700
Data Index: 3837656 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 6209114 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 1032287 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 4970327 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 2658576 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1819. Min Act: -0.1700
Data Index: 8774548 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1194. Min Act: -0.1700
Data Index: 3649051 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1194. Min Act: -0.1700
Data Index: 4529845 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1194. Min Act: -0.1700
Data Index: 4664579 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1194. Min Act: -0.1700
Data Index: 3281831 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6194. Min Range: -8.6194
Max Act: 8.1194. Min Act: -0.1700
Data Index: 4269114 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19