Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.4143. Min Act: -0.1700
Data Index: 8109444 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2893. Min Act: -0.1700
Data Index: 8820636 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2581. Min Act: -0.1700
Data Index: 5690674 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.2268. Min Act: -0.1700
Data Index: 1691839 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1331. Min Act: -0.1700
Data Index: 379484 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1331. Min Act: -0.1700
Data Index: 1368359 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1018. Min Act: -0.1700
Data Index: 5123917 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1331. Min Act: -0.1700
Data Index: 4927375 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1018. Min Act: -0.1700
Data Index: 4304909 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 4542333 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8616847 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8298475 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 8217045 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0393. Min Act: -0.1700
Data Index: 597271 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.1018. Min Act: -0.1700
Data Index: 7580881 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 497131 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0393. Min Act: -0.1700
Data Index: 933417 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0393. Min Act: -0.1700
Data Index: 8195065 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0393. Min Act: -0.1700
Data Index: 3961486 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4143. Min Range: -5.4143
Max Act: 5.0706. Min Act: -0.1700
Data Index: 4402822 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19