Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.5280. Min Act: -0.1700
Data Index: 6396707 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.5474. Min Act: -0.1700
Data Index: 4529904 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.5026. Min Act: -0.1700
Data Index: 4341097 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.5055. Min Act: -0.1700
Data Index: 5834810 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.5074. Min Act: -0.1700
Data Index: 886776 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4942. Min Act: -0.1700
Data Index: 4651238 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4776. Min Act: -0.1700
Data Index: 2491723 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4508. Min Act: -0.1700
Data Index: 1404779 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4682. Min Act: -0.1700
Data Index: 1183992 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4602. Min Act: -0.1700
Data Index: 5037489 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4528. Min Act: -0.1700
Data Index: 5528307 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4559. Min Act: -0.1700
Data Index: 4297108 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4628. Min Act: -0.1700
Data Index: 4065361 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4305. Min Act: -0.1700
Data Index: 205846 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4394. Min Act: -0.1700
Data Index: 1735127 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4158. Min Act: -0.1700
Data Index: 2288948 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4246. Min Act: -0.1700
Data Index: 7278640 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4526. Min Act: -0.1700
Data Index: 2222856 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.4134. Min Act: -0.1700
Data Index: 8622698 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.5474. Min Range: -3.5474
Max Act: 3.3991. Min Act: -0.1700
Data Index: 1530077 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full textTruncated
Full Text #19