Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0693. Min Range: -7.0693
Max Act: 7.0693. Min Act: -0.1700
Data Index: 5101687 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0693. Min Range: -7.0693
Max Act: 7.0380. Min Act: -0.1700
Data Index: 8099045 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0693. Min Range: -7.0693
Max Act: 7.0380. Min Act: -0.1700
Data Index: 1956698 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0693. Min Range: -7.0693
Max Act: 7.0068. Min Act: -0.1700
Data Index: 7467189 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9755. Min Act: -0.1700
Data Index: 8093570 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9755. Min Act: -0.1700
Data Index: 7275365 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9755. Min Act: -0.1700
Data Index: 5779765 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 5184349 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 461232 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 3543881 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 7252629 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 7915935 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 7899453 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 2669728 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9130. Min Act: -0.1700
Data Index: 6361454 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9130. Min Act: -0.1700
Data Index: 6203608 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9443. Min Act: -0.1700
Data Index: 3736936 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.9130. Min Act: -0.1700
Data Index: 1500395 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.8818. Min Act: -0.1700
Data Index: 2519719 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0693. Min Range: -7.0693
Max Act: 6.8818. Min Act: -0.1700
Data Index: 2155672 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19