Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.4121. Min Act: -0.1700
Data Index: 8680909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.3496. Min Act: -0.1700
Data Index: 6826813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.3496. Min Act: -0.1700
Data Index: 5836323 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2871. Min Act: -0.1700
Data Index: 8282788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2871. Min Act: -0.1700
Data Index: 5156464 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2871. Min Act: -0.1700
Data Index: 479858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2559. Min Act: -0.1700
Data Index: 2813216 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2559. Min Act: -0.1700
Data Index: 2867173 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2246. Min Act: -0.1700
Data Index: 4128135 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2246. Min Act: -0.1700
Data Index: 1866450 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.2246. Min Act: -0.1700
Data Index: 1894558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1700
Data Index: 1732418 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1700
Data Index: 6426499 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1934. Min Act: -0.1700
Data Index: 906460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1934. Min Act: -0.1700
Data Index: 745690 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1700
Data Index: 3214681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1695
Data Index: 6262723 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1700
Data Index: 343099 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1621. Min Act: -0.1700
Data Index: 3217028 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4121. Min Range: -4.4121
Max Act: 4.1934. Min Act: -0.1700
Data Index: 4240518 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19