Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2128 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1369. Min Range: -6.1369
Max Act: 6.1369. Min Act: -0.1700
Data Index: 6916642 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1369. Min Range: -6.1369
Max Act: 6.0432. Min Act: -0.1700
Data Index: 1687121 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1369. Min Range: -6.1369
Max Act: 6.0119. Min Act: -0.1700
Data Index: 2156037 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.9494. Min Act: -0.1700
Data Index: 8536161 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.8869. Min Act: -0.1700
Data Index: 800417 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.8557. Min Act: -0.1700
Data Index: 3446491 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.8244. Min Act: -0.1700
Data Index: 8560650 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.7932. Min Act: -0.1700
Data Index: 3122652 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.7619. Min Act: -0.1700
Data Index: 5105585 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.7619. Min Act: -0.1700
Data Index: 7523305 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.7307. Min Act: -0.1700
Data Index: 3851404 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6994. Min Act: -0.1700
Data Index: 3275400 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6994. Min Act: -0.1700
Data Index: 2091331 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.7307. Min Act: -0.1700
Data Index: 553349 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6682. Min Act: -0.1700
Data Index: 5266668 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6682. Min Act: -0.1700
Data Index: 3582135 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6682. Min Act: -0.1700
Data Index: 4447763 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6682. Min Act: -0.1700
Data Index: 8560649 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6682. Min Act: -0.1700
Data Index: 6909402 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1369. Min Range: -6.1369
Max Act: 5.6369. Min Act: -0.1700
Data Index: 2552023 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19