Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.9062. Min Act: -0.1700
Data Index: 7646904 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.7498. Min Act: -0.1700
Data Index: 4341649 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.6559. Min Act: -0.1700
Data Index: 6502762 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.6403. Min Act: -0.1700
Data Index: 4740011 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.6246. Min Act: -0.1700
Data Index: 4534196 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.5464. Min Act: -0.1700
Data Index: 1717651 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.5464. Min Act: -0.1700
Data Index: 6255670 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.5307. Min Act: -0.1700
Data Index: 1976354 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4837. Min Act: -0.1700
Data Index: 7896059 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4681. Min Act: -0.1700
Data Index: 6779893 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4524. Min Act: -0.1700
Data Index: 4651935 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4524. Min Act: -0.1700
Data Index: 4249221 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4367. Min Act: -0.1700
Data Index: 8453191 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4211. Min Act: -0.1700
Data Index: 2657221 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4367. Min Act: -0.1700
Data Index: 6017308 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4367. Min Act: -0.1700
Data Index: 177101 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4211. Min Act: -0.1700
Data Index: 692627 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4211. Min Act: -0.1700
Data Index: 5671358 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4211. Min Act: -0.1700
Data Index: 8519515 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9062. Min Range: -3.9062
Max Act: 3.4367. Min Act: -0.1700
Data Index: 6003756 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19