Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.6103. Min Act: -0.1700
Data Index: 7347163 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.5477. Min Act: -0.1700
Data Index: 843058 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.5163. Min Act: -0.1700
Data Index: 4041420 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.5007. Min Act: -0.1700
Data Index: 6652043 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4850. Min Act: -0.1700
Data Index: 3209021 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4850. Min Act: -0.1700
Data Index: 1663627 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.5163. Min Act: -0.1700
Data Index: 8652303 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4850. Min Act: -0.1700
Data Index: 3261942 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.5007. Min Act: -0.1700
Data Index: 1327840 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4850. Min Act: -0.1700
Data Index: 5852467 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4380. Min Act: -0.1700
Data Index: 2696820 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4537. Min Act: -0.1700
Data Index: 4097375 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4693. Min Act: -0.1700
Data Index: 1636657 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4537. Min Act: -0.1700
Data Index: 928840 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4850. Min Act: -0.1700
Data Index: 5415365 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4693. Min Act: -0.1700
Data Index: 451607 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4693. Min Act: -0.1700
Data Index: 6330028 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4693. Min Act: -0.1700
Data Index: 1188597 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4537. Min Act: -0.1700
Data Index: 3040596 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6103. Min Range: -3.6103
Max Act: 3.4537. Min Act: -0.1700
Data Index: 2038658 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19