Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0168. Min Range: -4.0168
Max Act: 4.0168. Min Act: -0.1700
Data Index: 8704652 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.9543. Min Act: -0.1700
Data Index: 5968217 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.9543. Min Act: -0.1700
Data Index: 2115755 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.8292. Min Act: -0.1700
Data Index: 3136443 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.8292. Min Act: -0.1700
Data Index: 848343 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.8136. Min Act: -0.1700
Data Index: 1389920 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.8292. Min Act: -0.1700
Data Index: 4369250 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7979. Min Act: -0.1700
Data Index: 4982843 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7979. Min Act: -0.1700
Data Index: 303784 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7979. Min Act: -0.1700
Data Index: 3282246 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7823. Min Act: -0.1700
Data Index: 868059 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7666. Min Act: -0.1700
Data Index: 7373602 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7354. Min Act: -0.1700
Data Index: 7037549 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7197. Min Act: -0.1700
Data Index: 5280116 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7354. Min Act: -0.1700
Data Index: 2900112 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7354. Min Act: -0.1700
Data Index: 4776810 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7510. Min Act: -0.1700
Data Index: 3913917 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.7041. Min Act: -0.1700
Data Index: 5717263 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.6884. Min Act: -0.1700
Data Index: 3024591 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0168. Min Range: -4.0168
Max Act: 3.6728. Min Act: -0.1700
Data Index: 636819 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19