Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2319 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.4239. Min Act: -0.1700
Data Index: 8791159 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.2364. Min Act: -0.1700
Data Index: 3267965 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1739. Min Act: -0.1700
Data Index: 1406084 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.2052. Min Act: -0.1700
Data Index: 8558988 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1114. Min Act: -0.1700
Data Index: 4673628 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1114. Min Act: -0.1700
Data Index: 2592058 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1114. Min Act: -0.1700
Data Index: 4116676 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1114. Min Act: -0.1700
Data Index: 8746901 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.1114. Min Act: -0.1700
Data Index: 2711642 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.0802. Min Act: -0.1700
Data Index: 40600 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4239. Min Range: -5.4239
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3718481 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.9239. Min Act: -0.1700
Data Index: 7540215 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.9552. Min Act: -0.1700
Data Index: 7655593 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.9239. Min Act: -0.1700
Data Index: 3678367 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.9552. Min Act: -0.1700
Data Index: 8182948 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.9239. Min Act: -0.1700
Data Index: 4207713 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.8927. Min Act: -0.1700
Data Index: 3020569 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.8614. Min Act: -0.1700
Data Index: 1905535 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.8927. Min Act: -0.1700
Data Index: 6934072 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4239. Min Range: -5.4239
Max Act: 4.8614. Min Act: -0.1700
Data Index: 7656763 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19