Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.6806. Min Act: -0.1700
Data Index: 4133504 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.6181. Min Act: -0.1700
Data Index: 6295556 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.5556. Min Act: -0.1700
Data Index: 6262645 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.5244. Min Act: -0.1700
Data Index: 4201751 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.4619. Min Act: -0.1700
Data Index: 4289485 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3994. Min Act: -0.1700
Data Index: 1474785 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3369. Min Act: -0.1700
Data Index: 4561751 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 8061094 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 2676609 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2744. Min Act: -0.1700
Data Index: 4092880 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 4707635 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 7735926 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 1420113 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.3056. Min Act: -0.1700
Data Index: 3410260 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2119. Min Act: -0.1700
Data Index: 3675274 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2431. Min Act: -0.1700
Data Index: 6046147 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2119. Min Act: -0.1700
Data Index: 6675511 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2431. Min Act: -0.1700
Data Index: 3373636 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2119. Min Act: -0.1700
Data Index: 3315150 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6806. Min Range: -7.6806
Max Act: 7.2119. Min Act: -0.1700
Data Index: 2611171 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19