Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5740 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.4851. Min Act: -0.1700
Data Index: 444869 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.5164. Min Act: -0.1700
Data Index: 5849574 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.2039. Min Act: -0.1700
Data Index: 2604488 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.2039. Min Act: -0.1700
Data Index: 6457212 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.1414. Min Act: -0.1700
Data Index: 3949280 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.1101. Min Act: -0.1700
Data Index: 8279238 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.0476. Min Act: -0.1700
Data Index: 2471126 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.0476. Min Act: -0.1700
Data Index: 947079 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.0164. Min Act: -0.1700
Data Index: 182816 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.0164. Min Act: -0.1700
Data Index: 5342133 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5164. Min Range: -7.5164
Max Act: 7.0476. Min Act: -0.1700
Data Index: 7164412 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9851. Min Act: -0.1700
Data Index: 2355136 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 6939566 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9539. Min Act: -0.1700
Data Index: 4921017 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 4012467 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 7296544 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.8914. Min Act: -0.1700
Data Index: 2471116 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 7447729 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 5445977 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5164. Min Range: -7.5164
Max Act: 6.9226. Min Act: -0.1700
Data Index: 1605481 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19