Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1716 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.9288. Min Act: -0.1700
Data Index: 6966906 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.8653. Min Act: -0.1700
Data Index: 1674774 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.8336. Min Act: -0.1700
Data Index: 1506561 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.7220. Min Act: -0.1700
Data Index: 3040424 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.7060. Min Act: -0.1700
Data Index: 339637 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.7379. Min Act: -0.1700
Data Index: 6349986 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.7060. Min Act: -0.1700
Data Index: 5716919 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6900. Min Act: -0.1700
Data Index: 7412191 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6740. Min Act: -0.1700
Data Index: 6039467 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6740. Min Act: -0.1700
Data Index: 6429335 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6419. Min Act: -0.1700
Data Index: 708350 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6097. Min Act: -0.1700
Data Index: 744546 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6419. Min Act: -0.1700
Data Index: 4897185 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6097. Min Act: -0.1700
Data Index: 3248810 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6097. Min Act: -0.1700
Data Index: 4538350 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.5936. Min Act: -0.1700
Data Index: 6040628 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.5936. Min Act: -0.1700
Data Index: 544552 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6097. Min Act: -0.1700
Data Index: 1113693 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.5936. Min Act: -0.1700
Data Index: 5000728 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9288. Min Range: -2.9288
Max Act: 2.6097. Min Act: -0.1700
Data Index: 7024672 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19