Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1178 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2895. Min Range: -4.2895
Max Act: 4.2895. Min Act: -0.1700
Data Index: 5571193 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.9769. Min Act: -0.1700
Data Index: 4575070 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.9457. Min Act: -0.1700
Data Index: 2795104 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.9144. Min Act: -0.1700
Data Index: 8799779 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.9144. Min Act: -0.1700
Data Index: 8304420 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8519. Min Act: -0.1700
Data Index: 7847329 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8206. Min Act: -0.1700
Data Index: 5563446 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8831. Min Act: -0.1700
Data Index: 3705689 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8519. Min Act: -0.1700
Data Index: 6789915 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8206. Min Act: -0.1700
Data Index: 5798833 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8206. Min Act: -0.1700
Data Index: 4002598 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7580. Min Act: -0.1700
Data Index: 7858196 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7893. Min Act: -0.1700
Data Index: 2646232 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7580. Min Act: -0.1700
Data Index: 6964348 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7424. Min Act: -0.1700
Data Index: 932240 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7893. Min Act: -0.1700
Data Index: 2475698 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7893. Min Act: -0.1700
Data Index: 8013812 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8206. Min Act: -0.1700
Data Index: 5926216 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.7893. Min Act: -0.1700
Data Index: 2638928 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2895. Min Range: -4.2895
Max Act: 3.8206. Min Act: -0.1700
Data Index: 506896 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19