Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.9249. Min Act: -0.1700
Data Index: 5132983 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8773. Min Act: -0.1700
Data Index: 3360867 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8615. Min Act: -0.1700
Data Index: 2377608 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8456. Min Act: -0.1700
Data Index: 1109285 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8297. Min Act: -0.1700
Data Index: 2537211 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 7141797 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 5244193 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 8549641 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 5634853 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 4232584 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 2875736 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7979. Min Act: -0.1700
Data Index: 6742231 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.8138. Min Act: -0.1700
Data Index: 1801735 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7819. Min Act: -0.1700
Data Index: 3572772 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 4788358 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7819. Min Act: -0.1700
Data Index: 5018332 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7500. Min Act: -0.1700
Data Index: 763998 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 1332294 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 6486190 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9249. Min Range: -2.9249
Max Act: 2.7660. Min Act: -0.1700
Data Index: 3041149 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19