Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.4109. Min Act: -0.1700
Data Index: 7324495 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.3484. Min Act: -0.1700
Data Index: 7102332 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.3484. Min Act: -0.1700
Data Index: 5515913 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.3172. Min Act: -0.1700
Data Index: 2497956 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.3172. Min Act: -0.1700
Data Index: 8376544 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2859. Min Act: -0.1700
Data Index: 1886040 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2546. Min Act: -0.1700
Data Index: 2367854 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2546. Min Act: -0.1700
Data Index: 338383 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 3681875 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2546. Min Act: -0.1700
Data Index: 7322504 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2546. Min Act: -0.1700
Data Index: 8660974 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 133106 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 8033695 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 5576155 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 8683958 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.1921. Min Act: -0.1700
Data Index: 2696022 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.1921. Min Act: -0.1700
Data Index: 1451964 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.2234. Min Act: -0.1700
Data Index: 1558320 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.1921. Min Act: -0.1700
Data Index: 331099 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4109. Min Range: -4.4109
Max Act: 4.1921. Min Act: -0.1700
Data Index: 4215395 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19