Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0330. Min Range: -4.0330
Max Act: 4.0330. Min Act: -0.1700
Data Index: 2449888 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0330. Min Range: -4.0330
Max Act: 4.0017. Min Act: -0.1700
Data Index: 2701299 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8767. Min Act: -0.1700
Data Index: 7093731 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 8233387 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8454. Min Act: -0.1700
Data Index: 8602282 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8454. Min Act: -0.1700
Data Index: 6247566 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8454. Min Act: -0.1700
Data Index: 5124274 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 8411609 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 5700262 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 2355013 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 3754274 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.8141. Min Act: -0.1700
Data Index: 8090760 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 1561602 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 4158699 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 7483244 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 2999930 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 8196917 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 6973196 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 6523567 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0330. Min Range: -4.0330
Max Act: 3.7829. Min Act: -0.1700
Data Index: 1506351 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19