Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.7764. Min Act: -0.1700
Data Index: 1695871 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.7126. Min Act: -0.1700
Data Index: 1135473 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.7126. Min Act: -0.1700
Data Index: 3263570 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6806. Min Act: -0.1700
Data Index: 6470557 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6164. Min Act: -0.1700
Data Index: 7512733 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6164. Min Act: -0.1700
Data Index: 3424225 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6164. Min Act: -0.1700
Data Index: 1142881 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5842. Min Act: -0.1700
Data Index: 6239922 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6164. Min Act: -0.1700
Data Index: 4879598 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5680. Min Act: -0.1700
Data Index: 5177987 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.6164. Min Act: -0.1700
Data Index: 8039181 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5680. Min Act: -0.1700
Data Index: 1861143 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5680. Min Act: -0.1700
Data Index: 4461011 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5519. Min Act: -0.1700
Data Index: 1669305 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5519. Min Act: -0.1700
Data Index: 2546921 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5196. Min Act: -0.1700
Data Index: 7674384 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5680. Min Act: -0.1700
Data Index: 7574768 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5358. Min Act: -0.1700
Data Index: 6782405 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5358. Min Act: -0.1700
Data Index: 1926959 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7764. Min Range: -2.7764
Max Act: 2.5358. Min Act: -0.1700
Data Index: 1889882 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19