Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4239272 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.5490. Min Act: -0.1700
Data Index: 2019896 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.1427. Min Act: -0.1700
Data Index: 5202602 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.1427. Min Act: -0.1700
Data Index: 7842744 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.0490. Min Act: -0.1700
Data Index: 5293386 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.0177. Min Act: -0.1700
Data Index: 6977106 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9865. Min Act: -0.1700
Data Index: 3917442 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.0177. Min Act: -0.1700
Data Index: 2909896 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9240. Min Act: -0.1700
Data Index: 3691738 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5802. Min Range: -5.5802
Max Act: 5.0177. Min Act: -0.1700
Data Index: 8487483 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9552. Min Act: -0.1700
Data Index: 2260011 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9552. Min Act: -0.1700
Data Index: 5213033 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.8927. Min Act: -0.1700
Data Index: 7641093 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9240. Min Act: -0.1700
Data Index: 828040 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.8927. Min Act: -0.1700
Data Index: 1059678 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9552. Min Act: -0.1700
Data Index: 7929090 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.8927. Min Act: -0.1700
Data Index: 7639432 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9240. Min Act: -0.1700
Data Index: 8750314 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9240. Min Act: -0.1700
Data Index: 6657392 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5802. Min Range: -5.5802
Max Act: 4.9240. Min Act: -0.1700
Data Index: 2524875 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19