Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2158 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.9764. Min Act: -0.1700
Data Index: 7065199 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.9764. Min Act: -0.1700
Data Index: 2090363 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1417224 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8983. Min Act: -0.1700
Data Index: 624996 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1331262 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1935973 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8826. Min Act: -0.1700
Data Index: 4783086 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8826. Min Act: -0.1700
Data Index: 5538931 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8670. Min Act: -0.1700
Data Index: 5039782 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8514. Min Act: -0.1700
Data Index: 3684904 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8357. Min Act: -0.1700
Data Index: 1972762 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8201. Min Act: -0.1700
Data Index: 4898691 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8044. Min Act: -0.1700
Data Index: 2096643 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8201. Min Act: -0.1700
Data Index: 6662281 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8201. Min Act: -0.1700
Data Index: 4370843 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.7888. Min Act: -0.1700
Data Index: 4113442 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8044. Min Act: -0.1700
Data Index: 5538927 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.7888. Min Act: -0.1700
Data Index: 6410292 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.7732. Min Act: -0.1700
Data Index: 2894240 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9764. Min Range: -3.9764
Max Act: 3.8044. Min Act: -0.1700
Data Index: 1233951 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19