Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.2413. Min Act: -0.1700
Data Index: 1723658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.2413. Min Act: -0.1700
Data Index: 2138438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1788. Min Act: -0.1700
Data Index: 5331539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1788. Min Act: -0.1700
Data Index: 8140110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.2100. Min Act: -0.1700
Data Index: 7507042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1035087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1475. Min Act: -0.1700
Data Index: 3413420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1163. Min Act: -0.1700
Data Index: 1644694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1163. Min Act: -0.1700
Data Index: 8674336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1163. Min Act: -0.1700
Data Index: 6779616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 1759069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3781253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 5554271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 6005514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 3281270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3405644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 6609206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0850. Min Act: -0.1700
Data Index: 6116234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0538. Min Act: -0.1700
Data Index: 3850458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2413. Min Range: -6.2413
Max Act: 6.0538. Min Act: -0.1700
Data Index: 3852262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19