Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.6401. Min Act: -0.1700
Data Index: 4529239 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.4838. Min Act: -0.1700
Data Index: 5576570 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.4526. Min Act: -0.1700
Data Index: 2919572 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.4213. Min Act: -0.1700
Data Index: 4528052 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.4213. Min Act: -0.1700
Data Index: 4150774 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3901. Min Act: -0.1700
Data Index: 1985460 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.4213. Min Act: -0.1700
Data Index: 2440829 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3901. Min Act: -0.1700
Data Index: 3170482 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3901. Min Act: -0.1700
Data Index: 994911 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3901. Min Act: -0.1700
Data Index: 3898490 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3901. Min Act: -0.1700
Data Index: 8769209 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 5687418 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3588. Min Act: -0.1700
Data Index: 7648798 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3588. Min Act: -0.1700
Data Index: 7281496 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 3695916 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 7526449 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 8260717 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6090321 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.3276. Min Act: -0.1700
Data Index: 7530249 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6401. Min Range: -5.6401
Max Act: 5.2963. Min Act: -0.1700
Data Index: 5538803 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19