Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.8233. Min Act: -0.1700
Data Index: 4992394 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.7608. Min Act: -0.1700
Data Index: 5024632 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.7296. Min Act: -0.1700
Data Index: 6038583 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.7296. Min Act: -0.1700
Data Index: 6199615 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6983. Min Act: -0.1700
Data Index: 7425960 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.7296. Min Act: -0.1700
Data Index: 4191381 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6671. Min Act: -0.1700
Data Index: 8439215 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6358. Min Act: -0.1700
Data Index: 3423049 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6358. Min Act: -0.1700
Data Index: 1198192 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6358. Min Act: -0.1700
Data Index: 7180431 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 3356754 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 863211 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5152484 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1295456 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1145548 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 6329278 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1201358 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 4811694 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 366316 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5421. Min Act: -0.1700
Data Index: 1167115 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19