Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1110. Min Range: -6.1110
Max Act: 6.1110. Min Act: -0.1700
Data Index: 8769940 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1110. Min Range: -6.1110
Max Act: 6.0797. Min Act: -0.1700
Data Index: 5983577 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1110. Min Range: -6.1110
Max Act: 6.0172. Min Act: -0.1700
Data Index: 3866514 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1110. Min Range: -6.1110
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4136736 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1110. Min Range: -6.1110
Max Act: 6.0172. Min Act: -0.1700
Data Index: 3301331 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5888127 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.8922. Min Act: -0.1700
Data Index: 7531289 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.8922. Min Act: -0.1700
Data Index: 724776 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.8610. Min Act: -0.1700
Data Index: 1358872 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.8610. Min Act: -0.1700
Data Index: 85053 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.8297. Min Act: -0.1700
Data Index: 2756896 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7985. Min Act: -0.1700
Data Index: 3227669 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7985. Min Act: -0.1700
Data Index: 1309084 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7985. Min Act: -0.1700
Data Index: 7769051 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7360. Min Act: -0.1700
Data Index: 62235 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7672. Min Act: -0.1700
Data Index: 2468027 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7672. Min Act: -0.1700
Data Index: 79418 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7672. Min Act: -0.1700
Data Index: 5972719 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7360. Min Act: -0.1700
Data Index: 6270623 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1110. Min Range: -6.1110
Max Act: 5.7360. Min Act: -0.1700
Data Index: 7039419 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19