Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 930 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.4275. Min Act: -0.1700
Data Index: 4035249 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3338. Min Act: -0.1700
Data Index: 3115821 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3650. Min Act: -0.1700
Data Index: 296948 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3338. Min Act: -0.1700
Data Index: 3217976 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3338. Min Act: -0.1700
Data Index: 97424 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3338. Min Act: -0.1682
Data Index: 2517301 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3338. Min Act: -0.1700
Data Index: 5194671 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 1589904 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 2183152 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 4844232 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1700
Data Index: 5034604 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 2164449 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 8303223 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.3025. Min Act: -0.1700
Data Index: 187210 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1697
Data Index: 3947723 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1700
Data Index: 4440250 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1699
Data Index: 1209809 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1700
Data Index: 590590 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2713. Min Act: -0.1695
Data Index: 6421553 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4275. Min Range: -6.4275
Max Act: 6.2400. Min Act: -0.1700
Data Index: 6781777 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19