Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4499 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.3380. Min Act: -0.1700
Data Index: 4374169 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2722. Min Act: -0.1700
Data Index: 5192259 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2557. Min Act: -0.1700
Data Index: 1385642 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2392. Min Act: -0.1700
Data Index: 3508727 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2392. Min Act: -0.1700
Data Index: 5192260 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2226. Min Act: -0.1700
Data Index: 6957438 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2226. Min Act: -0.1700
Data Index: 279104 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2392. Min Act: -0.1700
Data Index: 1514331 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2226. Min Act: -0.1700
Data Index: 7693874 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2060. Min Act: -0.1700
Data Index: 6531287 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2060. Min Act: -0.1700
Data Index: 4374168 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1894. Min Act: -0.1700
Data Index: 3447524 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1894. Min Act: -0.1700
Data Index: 1010787 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1894. Min Act: -0.1700
Data Index: 880521 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.2060. Min Act: -0.1700
Data Index: 1222734 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1728. Min Act: -0.1700
Data Index: 4374172 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1728. Min Act: -0.1700
Data Index: 5373236 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1728. Min Act: -0.1700
Data Index: 3734283 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1894. Min Act: -0.1700
Data Index: 1389773 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3380. Min Range: -2.3380
Max Act: 2.1728. Min Act: -0.1700
Data Index: 8348376 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19