Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.8136. Min Act: -0.1700
Data Index: 5345509 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7976. Min Act: -0.1700
Data Index: 1817538 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7976. Min Act: -0.1700
Data Index: 2975375 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7976. Min Act: -0.1700
Data Index: 3475704 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7817. Min Act: -0.1700
Data Index: 5692963 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7817. Min Act: -0.1700
Data Index: 5857623 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 1039422 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7817. Min Act: -0.1700
Data Index: 386791 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7817. Min Act: -0.1700
Data Index: 7908797 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 601637 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 2249153 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 2224535 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 7054697 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 6312138 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7658. Min Act: -0.1700
Data Index: 1856855 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7498. Min Act: -0.1700
Data Index: 4431449 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7498. Min Act: -0.1700
Data Index: 4925733 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7498. Min Act: -0.1700
Data Index: 394068 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7338. Min Act: -0.1700
Data Index: 498615 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8136. Min Range: -2.8136
Max Act: 2.7338. Min Act: -0.1700
Data Index: 1921842 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19