Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0036. Min Range: -7.0036
Max Act: 7.0036. Min Act: -0.1700
Data Index: 553931 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0036. Min Range: -7.0036
Max Act: 7.0036. Min Act: -0.1700
Data Index: 7087101 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.9724. Min Act: -0.1700
Data Index: 3993624 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.9724. Min Act: -0.1700
Data Index: 7473997 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.8786. Min Act: -0.1700
Data Index: 2852843 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.8161. Min Act: -0.1700
Data Index: 2042004 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7849. Min Act: -0.1700
Data Index: 6405623 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.8161. Min Act: -0.1700
Data Index: 3116240 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7849. Min Act: -0.1700
Data Index: 1492423 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7536. Min Act: -0.1700
Data Index: 1952642 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 5169084 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 2569884 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 1819362 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 5048555 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 8209480 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 6840925 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 8651482 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6911. Min Act: -0.1700
Data Index: 774946 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6911. Min Act: -0.1700
Data Index: 7446953 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6911. Min Act: -0.1700
Data Index: 383251 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19