Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5791. Min Act: -0.1700
Data Index: 2493081 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5947. Min Act: -0.1700
Data Index: 1912361 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5791. Min Act: -0.1700
Data Index: 1464482 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5478. Min Act: -0.1700
Data Index: 2306689 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5165. Min Act: -0.1700
Data Index: 5488298 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5008. Min Act: -0.1700
Data Index: 2800192 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5008. Min Act: -0.1700
Data Index: 4278188 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4695. Min Act: -0.1700
Data Index: 6205429 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4695. Min Act: -0.1700
Data Index: 8056291 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5008. Min Act: -0.1700
Data Index: 899287 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.5008. Min Act: -0.1700
Data Index: 1922517 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4695. Min Act: -0.1700
Data Index: 4219947 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4538. Min Act: -0.1700
Data Index: 3726566 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4695. Min Act: -0.1700
Data Index: 4421082 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4695. Min Act: -0.1700
Data Index: 2845701 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4538. Min Act: -0.1700
Data Index: 2755937 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4381. Min Act: -0.1700
Data Index: 7693249 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4538. Min Act: -0.1700
Data Index: 4900054 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4381. Min Act: -0.1700
Data Index: 3602492 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5947. Min Range: -3.5947
Max Act: 3.4225. Min Act: -0.1700
Data Index: 7693243 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19