Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.2441. Min Act: -0.1700
Data Index: 2548864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.2129. Min Act: -0.1700
Data Index: 983310 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1816. Min Act: -0.1700
Data Index: 3009642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1816. Min Act: -0.1697
Data Index: 1256253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1504. Min Act: -0.1700
Data Index: 5472745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1816. Min Act: -0.1700
Data Index: 6486477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1504. Min Act: -0.1700
Data Index: 58816 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1700
Data Index: 5237012 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1693
Data Index: 2474300 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1700
Data Index: 773958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1700
Data Index: 3216342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 4527167 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1699
Data Index: 8795705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 8743564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 3443720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 634318 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.1191. Min Act: -0.1700
Data Index: 399427 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 7117403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 2402922 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2441. Min Range: -4.2441
Max Act: 4.0879. Min Act: -0.1700
Data Index: 1299299 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19