Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2125 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.6843. Min Act: -0.1700
Data Index: 2543576 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.5593. Min Act: -0.1700
Data Index: 1843662 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.4343. Min Act: -0.1700
Data Index: 3700891 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.4343. Min Act: -0.1700
Data Index: 410315 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.3718. Min Act: -0.1700
Data Index: 4318636 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.3718. Min Act: -0.1700
Data Index: 6974617 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.2468. Min Act: -0.1700
Data Index: 1609992 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.1843. Min Act: -0.1700
Data Index: 3193577 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.1218. Min Act: -0.1700
Data Index: 2120284 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.1843. Min Act: -0.1700
Data Index: 1083221 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.1218. Min Act: -0.1700
Data Index: 1903919 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 1700170 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 5375708 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 2562248 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 5207804 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 3807568 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6843. Min Range: -9.6843
Max Act: 8.9968. Min Act: -0.1700
Data Index: 142699 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 6267863 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 1009832 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6843. Min Range: -9.6843
Max Act: 9.0593. Min Act: -0.1700
Data Index: 5575568 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19