Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1011 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.3943. Min Act: -0.1700
Data Index: 8481818 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.3943. Min Act: -0.1700
Data Index: 2951209 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.3780. Min Act: -0.1700
Data Index: 8234362 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.3943. Min Act: -0.1700
Data Index: 1003736 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.3124. Min Act: -0.1700
Data Index: 7443554 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2959. Min Act: -0.1700
Data Index: 3517384 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2630. Min Act: -0.1700
Data Index: 2301853 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2630. Min Act: -0.1700
Data Index: 3162943 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2630. Min Act: -0.1700
Data Index: 3272327 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2465. Min Act: -0.1700
Data Index: 5244708 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2630. Min Act: -0.1700
Data Index: 6209984 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2299. Min Act: -0.1700
Data Index: 7778424 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2134. Min Act: -0.1700
Data Index: 82654 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2465. Min Act: -0.1700
Data Index: 1117809 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2299. Min Act: -0.1700
Data Index: 4309652 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2134. Min Act: -0.1700
Data Index: 3376066 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.1968. Min Act: -0.1700
Data Index: 587472 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.2134. Min Act: -0.1700
Data Index: 6866101 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.1968. Min Act: -0.1700
Data Index: 7085992 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3943. Min Range: -2.3943
Max Act: 2.1802. Min Act: -0.1700
Data Index: 6499403 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19