Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.3395. Min Act: -0.1700
Data Index: 6549148 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.3082. Min Act: -0.1700
Data Index: 4328878 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.3082. Min Act: -0.1700
Data Index: 1422160 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2770. Min Act: -0.1700
Data Index: 4876482 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2457. Min Act: -0.1700
Data Index: 4055388 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2457. Min Act: -0.1700
Data Index: 6424122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2457. Min Act: -0.1700
Data Index: 4773984 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2457. Min Act: -0.1700
Data Index: 7660743 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 1319727 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2457. Min Act: -0.1700
Data Index: 5756644 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 6490501 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 8811118 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 6287697 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 4593150 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 5729536 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 521652 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 661854 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 5147674 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 4235288 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1832. Min Act: -0.1700
Data Index: 2182766 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19