Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.7143. Min Act: -0.1700
Data Index: 5582200 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.3705. Min Act: -0.1700
Data Index: 5771205 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.2455. Min Act: -0.1700
Data Index: 3409498 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.2143. Min Act: -0.1700
Data Index: 2846451 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.2143. Min Act: -0.1700
Data Index: 8005501 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.1517. Min Act: -0.1700
Data Index: 6822183 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.1517. Min Act: -0.1700
Data Index: 8790455 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.1517. Min Act: -0.1700
Data Index: 613043 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.1205. Min Act: -0.1700
Data Index: 7962504 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0892. Min Act: -0.1700
Data Index: 6329464 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0892. Min Act: -0.1700
Data Index: 8327402 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0892. Min Act: -0.1700
Data Index: 3145059 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.1205. Min Act: -0.1700
Data Index: 391924 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 1924457 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 4051930 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0892. Min Act: -0.1700
Data Index: 135693 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 8041439 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 536156 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 994358 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7143. Min Range: -4.7143
Max Act: 4.0580. Min Act: -0.1700
Data Index: 4949252 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19