Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.5151. Min Act: -0.1700
Data Index: 8503705 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.4526. Min Act: -0.1700
Data Index: 8503707 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.3901. Min Act: -0.1700
Data Index: 8352364 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.2963. Min Act: -0.1700
Data Index: 4479723 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1713. Min Act: -0.1700
Data Index: 8503704 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.2026. Min Act: -0.1700
Data Index: 1647003 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.2026. Min Act: -0.1700
Data Index: 1102180 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1713. Min Act: -0.1700
Data Index: 8802101 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1713. Min Act: -0.1700
Data Index: 2946344 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1401. Min Act: -0.1700
Data Index: 1458591 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1401. Min Act: -0.1700
Data Index: 7726567 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1401. Min Act: -0.1700
Data Index: 1637670 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1088. Min Act: -0.1700
Data Index: 8726641 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1088. Min Act: -0.1700
Data Index: 8503708 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.1088. Min Act: -0.1700
Data Index: 5003360 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.0776. Min Act: -0.1700
Data Index: 8337282 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.0463. Min Act: -0.1700
Data Index: 847948 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.0463. Min Act: -0.1700
Data Index: 8352367 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.0151. Min Act: -0.1700
Data Index: 7921606 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5151. Min Range: -7.5151
Max Act: 7.0151. Min Act: -0.1700
Data Index: 93697 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19