Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5631 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.2429. Min Act: -0.1700
Data Index: 8687719 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.2117. Min Act: -0.1700
Data Index: 3467046 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.0867. Min Act: -0.1700
Data Index: 6419429 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.1179. Min Act: -0.1700
Data Index: 2497786 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.1179. Min Act: -0.1700
Data Index: 8638585 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.0554. Min Act: -0.1700
Data Index: 2208262 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2429. Min Range: -4.2429
Max Act: 4.0242. Min Act: -0.1700
Data Index: 2183824 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.9304. Min Act: -0.1700
Data Index: 7427387 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8991. Min Act: -0.1700
Data Index: 768952 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8678. Min Act: -0.1700
Data Index: 1638270 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8678. Min Act: -0.1700
Data Index: 3236090 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8053. Min Act: -0.1700
Data Index: 6572160 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8053. Min Act: -0.1700
Data Index: 3907281 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.8053. Min Act: -0.1700
Data Index: 1638265 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.7740. Min Act: -0.1700
Data Index: 6454220 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.7584. Min Act: -0.1700
Data Index: 2051004 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.7584. Min Act: -0.1700
Data Index: 7550945 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.7584. Min Act: -0.1700
Data Index: 1206634 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.7115. Min Act: -0.1700
Data Index: 6454222 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2429. Min Range: -4.2429
Max Act: 3.6958. Min Act: -0.1700
Data Index: 7719019 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19