Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.3143. Min Act: -0.1700
Data Index: 4840535 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.2518. Min Act: -0.1700
Data Index: 832877 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.0330. Min Act: -0.1700
Data Index: 7111971 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.0330. Min Act: -0.1700
Data Index: 4450070 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.0330. Min Act: -0.1700
Data Index: 1810376 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3143. Min Range: -6.3143
Max Act: 6.0018. Min Act: -0.1700
Data Index: 1030172 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9705. Min Act: -0.1700
Data Index: 3281177 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 2912170 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 6116170 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3098079 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 2177578 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9080. Min Act: -0.1700
Data Index: 8443 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9080. Min Act: -0.1700
Data Index: 7063058 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.8768. Min Act: -0.1700
Data Index: 21737 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.8768. Min Act: -0.1700
Data Index: 3131452 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9080. Min Act: -0.1700
Data Index: 367099 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1555571 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.8768. Min Act: -0.1700
Data Index: 4318688 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.9080. Min Act: -0.1700
Data Index: 877343 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3143. Min Range: -6.3143
Max Act: 5.8455. Min Act: -0.1700
Data Index: 5993561 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19