Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.7291. Min Act: -0.1700
Data Index: 5939413 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.6041. Min Act: -0.1700
Data Index: 5412991 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.5416. Min Act: -0.1700
Data Index: 7595950 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.4478. Min Act: -0.1700
Data Index: 4370095 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.4478. Min Act: -0.1700
Data Index: 7650488 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3853. Min Act: -0.1700
Data Index: 4884828 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3853. Min Act: -0.1700
Data Index: 2148123 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 832716 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2916. Min Act: -0.1700
Data Index: 1552417 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 857108 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 461460 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 3216405 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3541. Min Act: -0.1700
Data Index: 6159502 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 6687392 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.3228. Min Act: -0.1700
Data Index: 154620 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2916. Min Act: -0.1700
Data Index: 2150109 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2603. Min Act: -0.1700
Data Index: 2481572 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2916. Min Act: -0.1700
Data Index: 682137 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2603. Min Act: -0.1700
Data Index: 1405772 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7291. Min Range: -5.7291
Max Act: 5.2291. Min Act: -0.1700
Data Index: 668147 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19