Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.9206. Min Act: -0.1700
Data Index: 713947 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.8581. Min Act: -0.1700
Data Index: 5376081 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.8581. Min Act: -0.1700
Data Index: 3473605 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.8893. Min Act: -0.1700
Data Index: 3824832 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.7018. Min Act: -0.1700
Data Index: 4842209 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.6706. Min Act: -0.1700
Data Index: 1326101 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.6393. Min Act: -0.1700
Data Index: 5346625 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.6393. Min Act: -0.1700
Data Index: 5525868 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.6393. Min Act: -0.1700
Data Index: 1679488 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3271830 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.5456. Min Act: -0.1700
Data Index: 6568177 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.5143. Min Act: -0.1700
Data Index: 7029922 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.5143. Min Act: -0.1700
Data Index: 8211681 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.4831. Min Act: -0.1700
Data Index: 5578059 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.4831. Min Act: -0.1700
Data Index: 3479002 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.4518. Min Act: -0.1700
Data Index: 8036 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.4518. Min Act: -0.1700
Data Index: 2306140 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.4206. Min Act: -0.1700
Data Index: 4826369 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.3893. Min Act: -0.1700
Data Index: 4578255 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9206. Min Range: -4.9206
Max Act: 4.3893. Min Act: -0.1700
Data Index: 7788267 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19