Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.3292. Min Act: -0.1700
Data Index: 7957829 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.3292. Min Act: -0.1700
Data Index: 5822989 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.3292. Min Act: -0.1700
Data Index: 4894223 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2980. Min Act: -0.1700
Data Index: 7487346 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2667. Min Act: -0.1700
Data Index: 1665248 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2667. Min Act: -0.1700
Data Index: 2711943 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2667. Min Act: -0.1700
Data Index: 703189 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2355. Min Act: -0.1700
Data Index: 8821078 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2042. Min Act: -0.1700
Data Index: 7748229 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2042. Min Act: -0.1700
Data Index: 8744397 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2042. Min Act: -0.1700
Data Index: 3114491 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5954287 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.2042. Min Act: -0.1700
Data Index: 1446513 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1730. Min Act: -0.1700
Data Index: 454584 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3181501 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1730. Min Act: -0.1700
Data Index: 7382009 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 2036422 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 6955 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1730. Min Act: -0.1700
Data Index: 5594020 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 5617111 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19