Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4140 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.6491. Min Act: -0.1700
Data Index: 1634027 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.6169. Min Act: -0.1700
Data Index: 2053037 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.6169. Min Act: -0.1700
Data Index: 7582546 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.6330. Min Act: -0.1700
Data Index: 7680844 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5847. Min Act: -0.1700
Data Index: 2930788 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.6008. Min Act: -0.1700
Data Index: 2272197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5686. Min Act: -0.1700
Data Index: 390061 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5847. Min Act: -0.1700
Data Index: 160099 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5686. Min Act: -0.1700
Data Index: 4629060 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5686. Min Act: -0.1700
Data Index: 3714 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5847. Min Act: -0.1700
Data Index: 6897015 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5686. Min Act: -0.1700
Data Index: 8650056 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1939396 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 8275322 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4351207 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4346913 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 527788 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 3759383 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 194355 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6491. Min Range: -2.6491
Max Act: 2.5525. Min Act: -0.1700
Data Index: 527783 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19