Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.9350. Min Act: -0.1700
Data Index: 5764762 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.8100. Min Act: -0.1700
Data Index: 3402756 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.7162. Min Act: -0.1700
Data Index: 7443132 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7443135 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6850. Min Act: -0.1700
Data Index: 4886445 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5912. Min Act: -0.1700
Data Index: 3703345 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1667242 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 3887733 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 3696580 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 3819009 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4975. Min Act: -0.1700
Data Index: 3402753 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 858273 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4975. Min Act: -0.1700
Data Index: 4689131 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4662. Min Act: -0.1700
Data Index: 5324570 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4662. Min Act: -0.1700
Data Index: 8712856 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1475166 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4662. Min Act: -0.1700
Data Index: 8438562 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4350. Min Act: -0.1700
Data Index: 4592412 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4350. Min Act: -0.1700
Data Index: 429676 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4350. Min Act: -0.1700
Data Index: 7136317 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19