Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2054. Min Range: -9.2054
Max Act: 9.2054. Min Act: -0.1700
Data Index: 3893968 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2054. Min Range: -9.2054
Max Act: 9.0804. Min Act: -0.1700
Data Index: 896851 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.8929. Min Act: -0.1700
Data Index: 2283185 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.8929. Min Act: -0.1700
Data Index: 4901113 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.7679. Min Act: -0.1700
Data Index: 2093908 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.7679. Min Act: -0.1700
Data Index: 193728 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.7054. Min Act: -0.1700
Data Index: 6145622 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.7054. Min Act: -0.1700
Data Index: 2834364 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.7054. Min Act: -0.1700
Data Index: 5417264 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5804. Min Act: -0.1700
Data Index: 8630111 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5804. Min Act: -0.1700
Data Index: 1716462 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5804. Min Act: -0.1700
Data Index: 8763560 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5804. Min Act: -0.1700
Data Index: 7625379 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5179. Min Act: -0.1700
Data Index: 2525060 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5179. Min Act: -0.1700
Data Index: 7000445 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5179. Min Act: -0.1700
Data Index: 5811978 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.4554. Min Act: -0.1700
Data Index: 7194079 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5804. Min Act: -0.1700
Data Index: 5412876 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.5179. Min Act: -0.1700
Data Index: 7774395 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2054. Min Range: -9.2054
Max Act: 8.4554. Min Act: -0.1700
Data Index: 2053635 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19