Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.8982. Min Act: -0.1700
Data Index: 1554695 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.9295. Min Act: -0.1700
Data Index: 4486243 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.7107. Min Act: -0.1700
Data Index: 1128079 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.6795. Min Act: -0.1700
Data Index: 1611690 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7117451 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.4920. Min Act: -0.1700
Data Index: 4386364 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.4920. Min Act: -0.1700
Data Index: 8659422 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.4295. Min Act: -0.1700
Data Index: 1065943 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3982. Min Act: -0.1700
Data Index: 7178865 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3982. Min Act: -0.1700
Data Index: 2187673 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3982. Min Act: -0.1700
Data Index: 6848823 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3670. Min Act: -0.1700
Data Index: 4915985 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3982. Min Act: -0.1700
Data Index: 1194495 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3670. Min Act: -0.1700
Data Index: 4469390 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3982. Min Act: -0.1700
Data Index: 2602761 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3357. Min Act: -0.1700
Data Index: 442625 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3670. Min Act: -0.1700
Data Index: 8128014 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2807482 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3670. Min Act: -0.1700
Data Index: 582803 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9295. Min Range: -6.9295
Max Act: 6.3045. Min Act: -0.1700
Data Index: 623755 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19