Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1451 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.4905. Min Act: -0.1700
Data Index: 3855435 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.4280. Min Act: -0.1700
Data Index: 3954863 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.3030. Min Act: -0.1700
Data Index: 237545 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2718. Min Act: -0.1700
Data Index: 6812782 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2718. Min Act: -0.1700
Data Index: 3762129 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2718. Min Act: -0.1700
Data Index: 3560274 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2405. Min Act: -0.1700
Data Index: 601750 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 601743 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 7494147 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 3235752 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.2093. Min Act: -0.1700
Data Index: 3235750 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1468. Min Act: -0.1700
Data Index: 3855450 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1468. Min Act: -0.1700
Data Index: 3385401 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1468. Min Act: -0.1700
Data Index: 3560255 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1155. Min Act: -0.1700
Data Index: 5673074 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1155. Min Act: -0.1700
Data Index: 3855444 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.1155. Min Act: -0.1700
Data Index: 7942329 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0843. Min Act: -0.1700
Data Index: 7362591 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0843. Min Act: -0.1700
Data Index: 1047044 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4905. Min Range: -5.4905
Max Act: 5.0843. Min Act: -0.1700
Data Index: 5551407 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19