Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.5069. Min Act: -0.1700
Data Index: 8201491 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.4757. Min Act: -0.1700
Data Index: 6967205 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.3819. Min Act: -0.1700
Data Index: 3359778 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.3507. Min Act: -0.1700
Data Index: 5640802 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.3507. Min Act: -0.1700
Data Index: 6696151 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.3194. Min Act: -0.1700
Data Index: 7210806 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2569. Min Act: -0.1700
Data Index: 8818278 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2257. Min Act: -0.1700
Data Index: 2356723 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2569. Min Act: -0.1700
Data Index: 3908801 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2257. Min Act: -0.1700
Data Index: 7444637 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2257. Min Act: -0.1700
Data Index: 2528589 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.2257. Min Act: -0.1700
Data Index: 6323958 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1944. Min Act: -0.1700
Data Index: 7431448 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1944. Min Act: -0.1700
Data Index: 7335334 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1632. Min Act: -0.1700
Data Index: 640992 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1632. Min Act: -0.1700
Data Index: 456218 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1319. Min Act: -0.1700
Data Index: 3022521 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1319. Min Act: -0.1700
Data Index: 7719557 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1632. Min Act: -0.1700
Data Index: 6783835 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5069. Min Range: -5.5069
Max Act: 5.1007. Min Act: -0.1700
Data Index: 8044026 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19