Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1589 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.8220. Min Act: -0.1700
Data Index: 8092343 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7742. Min Act: -0.1700
Data Index: 8638404 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7423. Min Act: -0.1700
Data Index: 7168420 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7263. Min Act: -0.1700
Data Index: 7574988 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1700
Data Index: 6280211 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7263. Min Act: -0.1700
Data Index: 6689469 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1527
Data Index: 1720957 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1699
Data Index: 3858580 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7263. Min Act: -0.0159
Data Index: 8818940 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1700
Data Index: 8808912 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1700
Data Index: 6002413 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7263. Min Act: -0.1700
Data Index: 2472147 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6943. Min Act: -0.1700
Data Index: 3652608 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1700
Data Index: 8391964 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6943. Min Act: -0.1699
Data Index: 8367602 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.7103. Min Act: -0.1700
Data Index: 248070 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6943. Min Act: -0.1700
Data Index: 4770135 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6783. Min Act: -0.1700
Data Index: 6423336 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6783. Min Act: -0.1700
Data Index: 1941539 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8220. Min Range: -2.8220
Max Act: 2.6943. Min Act: -0.1700
Data Index: 6504314 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19