Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.8193. Min Act: -0.1700
Data Index: 7494621 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.7881. Min Act: -0.1700
Data Index: 6307607 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.7881. Min Act: -0.1700
Data Index: 5109009 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.7568. Min Act: -0.1700
Data Index: 3091234 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.7256. Min Act: -0.1700
Data Index: 4009218 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4921182 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.7568. Min Act: -0.1700
Data Index: 7820190 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6943. Min Act: -0.1700
Data Index: 1947642 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6943. Min Act: -0.1700
Data Index: 8698089 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6943. Min Act: -0.1700
Data Index: 7967682 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6943. Min Act: -0.1700
Data Index: 2253899 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6631. Min Act: -0.1700
Data Index: 3433699 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 4671668 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6006. Min Act: -0.1700
Data Index: 4143506 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 6708400 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 5193789 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 1495145 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6006. Min Act: -0.1700
Data Index: 308131 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 2685288 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8193. Min Range: -4.8193
Max Act: 4.6318. Min Act: -0.1700
Data Index: 3316360 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19