Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4545 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.7097. Min Act: -0.1700
Data Index: 1269778 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.6472. Min Act: -0.1700
Data Index: 7895675 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.6472. Min Act: -0.1700
Data Index: 2317231 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.6159. Min Act: -0.1700
Data Index: 8831558 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.6159. Min Act: -0.1700
Data Index: 2317230 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5847. Min Act: -0.1700
Data Index: 4867456 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5847. Min Act: -0.1700
Data Index: 5382752 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5847. Min Act: -0.1700
Data Index: 7100334 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5847. Min Act: -0.1700
Data Index: 623309 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5534. Min Act: -0.1700
Data Index: 2885307 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5534. Min Act: -0.1700
Data Index: 3455444 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5222. Min Act: -0.1700
Data Index: 1679416 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5534. Min Act: -0.1700
Data Index: 661456 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5534. Min Act: -0.1700
Data Index: 2886412 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5534. Min Act: -0.1700
Data Index: 6108800 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.5222. Min Act: -0.1700
Data Index: 144011 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.4597. Min Act: -0.1700
Data Index: 2057256 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.4909. Min Act: -0.1700
Data Index: 4518456 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.4597. Min Act: -0.1700
Data Index: 6853946 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7097. Min Range: -4.7097
Max Act: 4.4597. Min Act: -0.1700
Data Index: 6921225 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19