Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.2304. Min Act: -0.1700
Data Index: 2745914 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 6667342 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 3060639 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0741. Min Act: -0.1700
Data Index: 3631321 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0428. Min Act: -0.1700
Data Index: 8378457 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0428. Min Act: -0.1700
Data Index: 5642890 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0428. Min Act: -0.1700
Data Index: 2713574 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0428. Min Act: -0.1700
Data Index: 4474972 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0428. Min Act: -0.1700
Data Index: 748514 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0741. Min Act: -0.1700
Data Index: 389225 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 2190715 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 3747798 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 325634 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 3393362 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 596533 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 4841310 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 5661898 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 2593280 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 5224465 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 815077 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19