Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.4203. Min Act: -0.1700
Data Index: 5246662 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.4203. Min Act: -0.1700
Data Index: 7995843 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2953. Min Act: -0.1700
Data Index: 7509725 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.3266. Min Act: -0.1700
Data Index: 6627432 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2953. Min Act: -0.1700
Data Index: 5246677 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 3660857 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2641. Min Act: -0.1700
Data Index: 8125705 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2953. Min Act: -0.1700
Data Index: 1807876 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2641. Min Act: -0.1700
Data Index: 6317340 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 8069175 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2016. Min Act: -0.1700
Data Index: 4627996 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 1807873 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 987311 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 6247303 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 5327475 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2328. Min Act: -0.1700
Data Index: 3894991 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2016. Min Act: -0.1700
Data Index: 699450 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2016. Min Act: -0.1700
Data Index: 5964169 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.2016. Min Act: -0.1700
Data Index: 5289575 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4203. Min Range: -6.4203
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1950251 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19