Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.3324. Min Act: -0.1700
Data Index: 6997025 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.3011. Min Act: -0.1700
Data Index: 4408346 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.2386. Min Act: -0.1700
Data Index: 1706120 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.2386. Min Act: -0.1700
Data Index: 5788971 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.2074. Min Act: -0.1700
Data Index: 4079494 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3606499 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1761. Min Act: -0.1700
Data Index: 5530032 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 789716 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5667528 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 3892309 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 3449585 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1136. Min Act: -0.1700
Data Index: 6224352 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1136. Min Act: -0.1700
Data Index: 1114570 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 3954749 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.1136. Min Act: -0.1700
Data Index: 552325 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 5943467 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 6647327 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 635227 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1975840 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3324. Min Range: -5.3324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1030920 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19