Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.5628. Min Act: -0.1700
Data Index: 746323 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.5628. Min Act: -0.1700
Data Index: 1488896 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.4378. Min Act: -0.1700
Data Index: 4525058 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3753. Min Act: -0.1700
Data Index: 5986823 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3753. Min Act: -0.1700
Data Index: 4410472 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3440. Min Act: -0.1700
Data Index: 3504664 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3440. Min Act: -0.1700
Data Index: 5429259 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2815. Min Act: -0.1700
Data Index: 2859190 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3128. Min Act: -0.1700
Data Index: 5795593 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 8804438 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2815. Min Act: -0.1700
Data Index: 4192658 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 7409554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 8612992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 5903563 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 2891284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 3735574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1559968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2815. Min Act: -0.1700
Data Index: 2569160 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 3189267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2190. Min Act: -0.1700
Data Index: 1954570 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19