Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5411 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.2022. Min Act: -0.1700
Data Index: 3679143 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.1085. Min Act: -0.1700
Data Index: 5519947 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.1085. Min Act: -0.1700
Data Index: 2852993 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.9522. Min Act: -0.1700
Data Index: 1993647 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.9834. Min Act: -0.1700
Data Index: 4736182 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.9209. Min Act: -0.1700
Data Index: 3077395 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8584. Min Act: -0.1700
Data Index: 8100223 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8584. Min Act: -0.1700
Data Index: 8271925 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8271. Min Act: -0.1700
Data Index: 5178649 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8584. Min Act: -0.1700
Data Index: 8271924 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8271. Min Act: -0.1700
Data Index: 6403719 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7958. Min Act: -0.1700
Data Index: 8125533 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7958. Min Act: -0.1700
Data Index: 7124408 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7958. Min Act: -0.1700
Data Index: 1752141 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7646. Min Act: -0.1700
Data Index: 5572803 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7333. Min Act: -0.1700
Data Index: 5519948 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7646. Min Act: -0.1700
Data Index: 4091113 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7646. Min Act: -0.1700
Data Index: 4280107 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7646. Min Act: -0.1700
Data Index: 6459561 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7646. Min Act: -0.1700
Data Index: 5754212 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19