Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.3161. Min Act: -0.1700
Data Index: 2160712 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.1598. Min Act: -0.1700
Data Index: 6852266 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.1598. Min Act: -0.1700
Data Index: 1760829 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 716729 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.1286. Min Act: -0.1700
Data Index: 4626826 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.1286. Min Act: -0.1700
Data Index: 4867481 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 618577 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 4944351 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 2288617 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 6457022 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 5498560 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 2979227 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0973. Min Act: -0.1700
Data Index: 2979228 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0660. Min Act: -0.1700
Data Index: 2039593 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0660. Min Act: -0.1700
Data Index: 4027424 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0348. Min Act: -0.1700
Data Index: 7220090 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0348. Min Act: -0.1700
Data Index: 6623478 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0348. Min Act: -0.1700
Data Index: 5339008 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0035. Min Act: -0.1700
Data Index: 5519965 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3161. Min Range: -4.3161
Max Act: 4.0035. Min Act: -0.1700
Data Index: 3107816 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19