Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 561 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1486. Min Act: -0.1700
Data Index: 6777770 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1486. Min Act: -0.1700
Data Index: 7614641 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1319. Min Act: -0.1700
Data Index: 122237 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1319. Min Act: -0.1699
Data Index: 8137968 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1152. Min Act: -0.1700
Data Index: 1976625 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.1152. Min Act: -0.1700
Data Index: 74569 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0985. Min Act: -0.1700
Data Index: 4450086 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0985. Min Act: -0.1700
Data Index: 5201221 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0985. Min Act: -0.1700
Data Index: 8637938 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0985. Min Act: -0.1700
Data Index: 1451160 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 2031694 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 6324318 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 2777846 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 1637256 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 7100016 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0817. Min Act: -0.1700
Data Index: 4180428 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0649. Min Act: -0.1700
Data Index: 6180173 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0649. Min Act: -0.1700
Data Index: 3371055 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0649. Min Act: -0.1700
Data Index: 593172 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1486. Min Range: -2.1486
Max Act: 2.0481. Min Act: -0.1700
Data Index: 2448675 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19