Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3973. Min Act: -0.1693
Data Index: 4182218 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.4062. Min Act: -0.1657
Data Index: 8072176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3709. Min Act: -0.1700
Data Index: 4086900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3709. Min Act: -0.1697
Data Index: 3189272 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3621. Min Act: -0.1700
Data Index: 7659937 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3621. Min Act: -0.1700
Data Index: 6930550 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3621. Min Act: -0.1700
Data Index: 7516213 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3533. Min Act: -0.1700
Data Index: 7232805 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3533. Min Act: -0.1699
Data Index: 4718830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3445. Min Act: -0.1700
Data Index: 7244851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3445. Min Act: -0.1695
Data Index: 272323 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3445. Min Act: -0.1688
Data Index: 80247 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3356. Min Act: -0.1648
Data Index: 841084 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3356. Min Act: -0.1700
Data Index: 4590964 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3445. Min Act: -0.1644
Data Index: 162689 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3356. Min Act: -0.1568
Data Index: 2706889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3356. Min Act: -0.1700
Data Index: 5075584 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3268. Min Act: -0.1699
Data Index: 6543787 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3268. Min Act: -0.1690
Data Index: 1014729 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4062. Min Range: -1.4062
Max Act: 1.3180. Min Act: -0.1700
Data Index: 2976377 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19