Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6202 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3998. Min Act: -0.1700
Data Index: 8053522 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3998. Min Act: -0.1700
Data Index: 8068764 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3469. Min Act: -0.1700
Data Index: 5488125 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3293. Min Act: -0.1700
Data Index: 6355299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3293. Min Act: -0.1700
Data Index: 680574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.3116. Min Act: -0.1700
Data Index: 2556633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2764. Min Act: -0.1700
Data Index: 7304756 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2764. Min Act: -0.1700
Data Index: 4242354 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2587. Min Act: -0.1700
Data Index: 5419535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2411. Min Act: -0.1700
Data Index: 739423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2411. Min Act: -0.1700
Data Index: 4392342 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2411. Min Act: -0.1700
Data Index: 6587402 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2235. Min Act: -0.1700
Data Index: 8563063 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2235. Min Act: -0.1700
Data Index: 3314332 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2147. Min Act: -0.1700
Data Index: 3605981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2147. Min Act: -0.1700
Data Index: 3722376 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2147. Min Act: -0.1700
Data Index: 1731873 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2059. Min Act: -0.1700
Data Index: 7047521 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.2059. Min Act: -0.1700
Data Index: 6260378 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3998. Min Range: -1.3998
Max Act: 1.1970. Min Act: -0.1700
Data Index: 3937279 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19