Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.6292. Min Act: -0.1700
Data Index: 3583769 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.5486. Min Act: -0.1700
Data Index: 8603183 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.5163. Min Act: -0.1700
Data Index: 4901281 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.5001. Min Act: -0.1700
Data Index: 7416772 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.5001. Min Act: -0.1700
Data Index: 8265233 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4839. Min Act: -0.1700
Data Index: 2246447 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4839. Min Act: -0.1700
Data Index: 2663841 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4839. Min Act: -0.1700
Data Index: 7519730 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4839. Min Act: -0.1700
Data Index: 5137032 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4514. Min Act: -0.1699
Data Index: 1348602 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4514. Min Act: -0.1699
Data Index: 3575310 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4514. Min Act: -0.1700
Data Index: 2455696 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4677. Min Act: -0.1700
Data Index: 4838184 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4677. Min Act: -0.1700
Data Index: 5372092 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4352. Min Act: -0.1699
Data Index: 506889 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4352. Min Act: -0.1700
Data Index: 5742511 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4352. Min Act: -0.1700
Data Index: 6153498 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4514. Min Act: -0.1700
Data Index: 27583 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4514. Min Act: -0.1700
Data Index: 7313454 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6292. Min Range: -2.6292
Max Act: 2.4352. Min Act: -0.1700
Data Index: 1522385 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19