Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 781 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.8114. Min Act: -0.1700
Data Index: 1570304 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1570310 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1570290 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7636. Min Act: -0.1700
Data Index: 1570293 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7157. Min Act: -0.1700
Data Index: 1570291 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7157. Min Act: -0.1700
Data Index: 1570285 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.7316. Min Act: -0.1700
Data Index: 1570279 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6837. Min Act: -0.1700
Data Index: 1570275 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6837. Min Act: -0.1700
Data Index: 6954801 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6837. Min Act: -0.1700
Data Index: 4228418 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6837. Min Act: -0.1699
Data Index: 1570308 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6676. Min Act: -0.1700
Data Index: 1570315 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6676. Min Act: -0.1700
Data Index: 6197328 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6516. Min Act: -0.1700
Data Index: 1570283 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6355. Min Act: -0.1700
Data Index: 1570309 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6355. Min Act: -0.1700
Data Index: 5019073 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6195. Min Act: -0.1700
Data Index: 1570316 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6195. Min Act: -0.1700
Data Index: 1028797 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6034. Min Act: -0.1700
Data Index: 2545420 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8114. Min Range: -2.8114
Max Act: 2.6034. Min Act: -0.1700
Data Index: 1570271 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19