Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0730. Min Range: -7.0730
Max Act: 7.0730. Min Act: -0.1700
Data Index: 2829596 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0730. Min Range: -7.0730
Max Act: 7.0418. Min Act: -0.1700
Data Index: 1648039 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.9793. Min Act: -0.1700
Data Index: 8385666 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.9480. Min Act: -0.1700
Data Index: 6055547 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.8230. Min Act: -0.1700
Data Index: 8385667 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6980. Min Act: -0.1700
Data Index: 1657579 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.7293. Min Act: -0.1700
Data Index: 3150638 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6355. Min Act: -0.1700
Data Index: 1928172 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6980. Min Act: -0.1700
Data Index: 8002159 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6668. Min Act: -0.1700
Data Index: 5599770 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 3450372 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6043. Min Act: -0.1700
Data Index: 8712402 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6043. Min Act: -0.1700
Data Index: 994117 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6355. Min Act: -0.1700
Data Index: 2829600 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 1648040 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6043. Min Act: -0.1700
Data Index: 6980798 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 325268 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.6043. Min Act: -0.1700
Data Index: 8029662 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 2517842 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0730. Min Range: -7.0730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 5178910 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19