Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.4819. Min Act: -0.1700
Data Index: 4326476 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.4506. Min Act: -0.1700
Data Index: 2584366 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.3256. Min Act: -0.1700
Data Index: 6080488 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.3256. Min Act: -0.1700
Data Index: 7963138 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2006. Min Act: -0.1700
Data Index: 901901 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.3569. Min Act: -0.1700
Data Index: 5819946 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 6773976 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2006. Min Act: -0.1700
Data Index: 7106672 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 4950655 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 4542228 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 8536833 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 908265 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.1693. Min Act: -0.1700
Data Index: 5485614 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2006. Min Act: -0.1700
Data Index: 8257780 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2006. Min Act: -0.1700
Data Index: 5479187 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2006. Min Act: -0.1700
Data Index: 5324847 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.2319. Min Act: -0.1700
Data Index: 7205214 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.1693. Min Act: -0.1700
Data Index: 1168183 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.1381. Min Act: -0.1700
Data Index: 6486843 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4819. Min Range: -4.4819
Max Act: 4.1068. Min Act: -0.1700
Data Index: 2007604 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19