Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.5629. Min Act: -0.1700
Data Index: 5817300 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.5004. Min Act: -0.1700
Data Index: 8211883 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.4691. Min Act: -0.1700
Data Index: 77640 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.4379. Min Act: -0.1700
Data Index: 1795300 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.4691. Min Act: -0.1700
Data Index: 4587210 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.4379. Min Act: -0.1700
Data Index: 3198422 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.3754. Min Act: -0.1700
Data Index: 3649042 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.3441. Min Act: -0.1700
Data Index: 509513 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.3129. Min Act: -0.1700
Data Index: 1001380 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5629421 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2816. Min Act: -0.1700
Data Index: 8162667 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2816. Min Act: -0.1700
Data Index: 967403 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2816. Min Act: -0.1700
Data Index: 6305194 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2504. Min Act: -0.1700
Data Index: 688195 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2504. Min Act: -0.1700
Data Index: 5453082 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.3129. Min Act: -0.1700
Data Index: 4785494 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2191. Min Act: -0.1700
Data Index: 5557973 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.2191. Min Act: -0.1700
Data Index: 5095370 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.1879. Min Act: -0.1700
Data Index: 4006217 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5629. Min Range: -5.5629
Max Act: 5.1879. Min Act: -0.1700
Data Index: 7503443 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19