Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.3514. Min Act: -0.1700
Data Index: 8025426 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.3357. Min Act: -0.1700
Data Index: 3807951 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2572. Min Act: -0.1700
Data Index: 7535415 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2572. Min Act: -0.1700
Data Index: 6125089 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2415. Min Act: -0.1700
Data Index: 2123981 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2258. Min Act: -0.1700
Data Index: 8654076 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2415. Min Act: -0.1700
Data Index: 6217687 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2415. Min Act: -0.1700
Data Index: 6713435 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2101. Min Act: -0.1700
Data Index: 2301116 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2101. Min Act: -0.1700
Data Index: 8100297 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1943. Min Act: -0.1700
Data Index: 3749983 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.2101. Min Act: -0.1700
Data Index: 656837 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1629. Min Act: -0.1700
Data Index: 332552 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1943. Min Act: -0.1700
Data Index: 1939191 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1629. Min Act: -0.1700
Data Index: 2427888 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1786. Min Act: -0.1700
Data Index: 5585512 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1786. Min Act: -0.1700
Data Index: 5345384 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1786. Min Act: -0.1700
Data Index: 1153820 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1629. Min Act: -0.1700
Data Index: 4676077 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3514. Min Range: -3.3514
Max Act: 3.1629. Min Act: -0.1700
Data Index: 8526838 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19