Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.4224. Min Act: -0.1700
Data Index: 3808551 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.4224. Min Act: -0.1700
Data Index: 84148 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.2661. Min Act: -0.1700
Data Index: 4002060 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.2661. Min Act: -0.1700
Data Index: 3882556 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.2036. Min Act: -0.1700
Data Index: 1247901 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.2036. Min Act: -0.1700
Data Index: 8270366 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1724. Min Act: -0.1700
Data Index: 2437113 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1724. Min Act: -0.1700
Data Index: 565687 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 4557953 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 1802420 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 1478003 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 6316368 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 6922552 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.1099. Min Act: -0.1700
Data Index: 6391010 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0786. Min Act: -0.1700
Data Index: 3109780 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0786. Min Act: -0.1700
Data Index: 6159159 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0474. Min Act: -0.1700
Data Index: 5527195 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0474. Min Act: -0.1700
Data Index: 136019 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0161. Min Act: -0.1700
Data Index: 5441201 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4224. Min Range: -5.4224
Max Act: 5.0161. Min Act: -0.1700
Data Index: 1043151 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19