Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.2240. Min Act: -0.1700
Data Index: 2670832 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.0990. Min Act: -0.1700
Data Index: 4142949 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.0365. Min Act: -0.1700
Data Index: 5506804 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.0365. Min Act: -0.1700
Data Index: 1532316 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.0052. Min Act: -0.1700
Data Index: 3972316 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9740. Min Act: -0.1700
Data Index: 7649549 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9740. Min Act: -0.1700
Data Index: 4771744 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9740. Min Act: -0.1700
Data Index: 7634172 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2240. Min Range: -7.2240
Max Act: 7.0052. Min Act: -0.1700
Data Index: 3063708 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9740. Min Act: -0.1700
Data Index: 70046 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1455859 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 2292533 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 9627 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 2916172 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1855540 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 2888676 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1503812 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.9115. Min Act: -0.1700
Data Index: 2062049 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.8802. Min Act: -0.1700
Data Index: 6474279 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2240. Min Range: -7.2240
Max Act: 6.8802. Min Act: -0.1700
Data Index: 2411463 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19