Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.9174. Min Act: -0.1700
Data Index: 5390491 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.8549. Min Act: -0.1700
Data Index: 6153826 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.7612. Min Act: -0.1700
Data Index: 6723859 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.7299. Min Act: -0.1700
Data Index: 5577289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.7299. Min Act: -0.1700
Data Index: 2957279 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.6987. Min Act: -0.1700
Data Index: 7214732 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.6987. Min Act: -0.1700
Data Index: 5167685 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.6674. Min Act: -0.1700
Data Index: 5039100 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.6362. Min Act: -0.1700
Data Index: 6635045 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.6049. Min Act: -0.1700
Data Index: 820173 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5737. Min Act: -0.1700
Data Index: 6802414 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5737. Min Act: -0.1700
Data Index: 756921 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5737. Min Act: -0.1700
Data Index: 7681286 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5112. Min Act: -0.1700
Data Index: 6004004 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5424. Min Act: -0.1700
Data Index: 5352539 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5112. Min Act: -0.1700
Data Index: 8527057 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.5112. Min Act: -0.1700
Data Index: 3804394 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.4799. Min Act: -0.1700
Data Index: 2331237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.4799. Min Act: -0.1700
Data Index: 5798202 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9174. Min Range: -4.9174
Max Act: 4.4799. Min Act: -0.1700
Data Index: 5777318 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19