Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 545453 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1899. Min Act: -0.1700
Data Index: 3280876 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1899. Min Act: -0.1700
Data Index: 543877 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1587. Min Act: -0.1700
Data Index: 1177261 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 1489751 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 7238845 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 4657446 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0962. Min Act: -0.1700
Data Index: 5663465 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 545454 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6315989 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0962. Min Act: -0.1700
Data Index: 492697 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0962. Min Act: -0.1700
Data Index: 8143937 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0962. Min Act: -0.1700
Data Index: 196114 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0649. Min Act: -0.1700
Data Index: 1479128 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0649. Min Act: -0.1700
Data Index: 3184531 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0649. Min Act: -0.1700
Data Index: 4400246 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2732007 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7769048 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0337. Min Act: -0.1700
Data Index: 5511546 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0024. Min Act: -0.1700
Data Index: 5362401 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19