Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3533. Min Range: -6.3533
Max Act: 6.3533. Min Act: -0.1700
Data Index: 5879022 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.7283. Min Act: -0.1700
Data Index: 6111231 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.6971. Min Act: -0.1700
Data Index: 2083590 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.6033. Min Act: -0.1700
Data Index: 3994323 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.5408. Min Act: -0.1700
Data Index: 805257 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.5096. Min Act: -0.1700
Data Index: 666345 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.4471. Min Act: -0.1700
Data Index: 6248588 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.4158. Min Act: -0.1700
Data Index: 3053535 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.4158. Min Act: -0.1700
Data Index: 7817858 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.3533. Min Act: -0.1700
Data Index: 7982231 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2596. Min Act: -0.1700
Data Index: 8241710 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2908. Min Act: -0.1700
Data Index: 5211856 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2908. Min Act: -0.1700
Data Index: 8478345 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3678380 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7666031 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2596. Min Act: -0.1700
Data Index: 1518740 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2596. Min Act: -0.1700
Data Index: 1323196 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.2283. Min Act: -0.1700
Data Index: 8526273 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.1971. Min Act: -0.1700
Data Index: 6019235 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3533. Min Range: -6.3533
Max Act: 5.1971. Min Act: -0.1700
Data Index: 8808213 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19