Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.7092. Min Act: -0.1700
Data Index: 8522312 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.6155. Min Act: -0.1700
Data Index: 2989922 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.5842. Min Act: -0.1700
Data Index: 802150 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.5842. Min Act: -0.1700
Data Index: 4694345 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.5530. Min Act: -0.1700
Data Index: 1991428 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.4905. Min Act: -0.1700
Data Index: 4040915 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.4905. Min Act: -0.1700
Data Index: 7373264 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.4280. Min Act: -0.1700
Data Index: 7843935 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.4280. Min Act: -0.1700
Data Index: 4084734 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.4592. Min Act: -0.1700
Data Index: 802149 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3655. Min Act: -0.1700
Data Index: 7276863 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3655. Min Act: -0.1700
Data Index: 2140236 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3342. Min Act: -0.1700
Data Index: 1735499 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3655. Min Act: -0.1700
Data Index: 1106611 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3342. Min Act: -0.1700
Data Index: 2153489 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3030. Min Act: -0.1700
Data Index: 7098512 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3030. Min Act: -0.1700
Data Index: 927502 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.3030. Min Act: -0.1700
Data Index: 5089761 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.2717. Min Act: -0.1700
Data Index: 4170758 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7092. Min Range: -6.7092
Max Act: 6.2717. Min Act: -0.1700
Data Index: 1958657 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19