Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4478 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1088. Min Range: -5.1088
Max Act: 5.1088. Min Act: -0.1700
Data Index: 7945660 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.9213. Min Act: -0.1700
Data Index: 4947305 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.8901. Min Act: -0.1700
Data Index: 6339783 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.8901. Min Act: -0.1700
Data Index: 6781870 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.8276. Min Act: -0.1700
Data Index: 3904486 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.8276. Min Act: -0.1700
Data Index: 7632180 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7651. Min Act: -0.1700
Data Index: 5691397 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 367195 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7963. Min Act: -0.1700
Data Index: 7603525 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7651. Min Act: -0.1700
Data Index: 3183317 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7026. Min Act: -0.1700
Data Index: 3815432 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 1105511 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 2680983 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 2641649 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 3183327 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 7447148 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7026. Min Act: -0.1700
Data Index: 3161913 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 4028371 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 2132111 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1088. Min Range: -5.1088
Max Act: 4.7338. Min Act: -0.1700
Data Index: 5711083 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19