Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2929. Min Range: -6.2929
Max Act: 6.2929. Min Act: -0.1700
Data Index: 2658171 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.9179. Min Act: -0.1700
Data Index: 3740118 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.9179. Min Act: -0.1700
Data Index: 7875833 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.8241. Min Act: -0.1700
Data Index: 2025072 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.8241. Min Act: -0.1700
Data Index: 1547400 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.7929. Min Act: -0.1700
Data Index: 4748425 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6991. Min Act: -0.1700
Data Index: 8334529 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6991. Min Act: -0.1700
Data Index: 4909908 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6679. Min Act: -0.1700
Data Index: 927182 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6991. Min Act: -0.1700
Data Index: 127829 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3918748 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3932941 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6366. Min Act: -0.1700
Data Index: 91391 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.5741. Min Act: -0.1700
Data Index: 2895703 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 1343826 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 1129910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 813291 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 4219441 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 615247 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2929. Min Range: -6.2929
Max Act: 5.6054. Min Act: -0.1700
Data Index: 988938 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19