Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1318 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.4007. Min Act: -0.1700
Data Index: 5569572 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.4007. Min Act: -0.1700
Data Index: 7431671 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.3850. Min Act: -0.1700
Data Index: 2495439 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.3693. Min Act: -0.1700
Data Index: 379256 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.3693. Min Act: -0.1700
Data Index: 8379754 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.3536. Min Act: -0.1700
Data Index: 229332 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.3223. Min Act: -0.1700
Data Index: 6525080 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.2752. Min Act: -0.1700
Data Index: 8351502 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.2280. Min Act: -0.1700
Data Index: 1454309 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.2437. Min Act: -0.1700
Data Index: 2117651 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.2123. Min Act: -0.1700
Data Index: 1974873 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.2280. Min Act: -0.1700
Data Index: 8195804 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1966. Min Act: -0.1700
Data Index: 7563473 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1808. Min Act: -0.1700
Data Index: 6523375 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1651. Min Act: -0.1700
Data Index: 2579086 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1808. Min Act: -0.1700
Data Index: 2364514 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1651. Min Act: -0.1700
Data Index: 6083211 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1494. Min Act: -0.1700
Data Index: 7893983 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1494. Min Act: -0.1700
Data Index: 602283 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4007. Min Range: -3.4007
Max Act: 3.1179. Min Act: -0.1700
Data Index: 6510059 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19