Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4626090 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.6388. Min Act: -0.1700
Data Index: 5958996 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.5763. Min Act: -0.1700
Data Index: 3398266 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.4825. Min Act: -0.1700
Data Index: 2108276 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.5138. Min Act: -0.1700
Data Index: 7636865 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.3575. Min Act: -0.1700
Data Index: 4626087 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.3888. Min Act: -0.1700
Data Index: 1166572 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.2950. Min Act: -0.1700
Data Index: 3107195 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.1700. Min Act: -0.1700
Data Index: 3690593 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.1388. Min Act: -0.1700
Data Index: 72713 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.1388. Min Act: -0.1700
Data Index: 940465 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.1388. Min Act: -0.1700
Data Index: 5548317 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0138. Min Act: -0.1700
Data Index: 7240724 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0450. Min Act: -0.1700
Data Index: 1474047 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0450. Min Act: -0.1700
Data Index: 1291130 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0138. Min Act: -0.1700
Data Index: 8600301 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6913541 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7950. Min Range: -5.7950
Max Act: 4.9513. Min Act: -0.1700
Data Index: 4811412 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7950. Min Range: -5.7950
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6718781 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7950. Min Range: -5.7950
Max Act: 4.9825. Min Act: -0.1700
Data Index: 6849706 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19