Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4203. Min Range: -5.4203
Max Act: 5.4203. Min Act: -0.1700
Data Index: 8475014 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4203. Min Range: -5.4203
Max Act: 5.1390. Min Act: -0.1700
Data Index: 732513 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4203. Min Range: -5.4203
Max Act: 5.0453. Min Act: -0.1700
Data Index: 800299 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4203. Min Range: -5.4203
Max Act: 5.0453. Min Act: -0.1700
Data Index: 700852 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9828. Min Act: -0.1700
Data Index: 4802936 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9828. Min Act: -0.1700
Data Index: 7017864 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4203. Min Range: -5.4203
Max Act: 5.0140. Min Act: -0.1700
Data Index: 7898471 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9828. Min Act: -0.1700
Data Index: 4362751 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9515. Min Act: -0.1700
Data Index: 4847882 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9515. Min Act: -0.1700
Data Index: 918717 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9515. Min Act: -0.1700
Data Index: 7898470 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9515. Min Act: -0.1700
Data Index: 8617337 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9203. Min Act: -0.1700
Data Index: 1183744 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8890. Min Act: -0.1700
Data Index: 3379709 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8890. Min Act: -0.1700
Data Index: 706618 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.9203. Min Act: -0.1700
Data Index: 1342284 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8578. Min Act: -0.1700
Data Index: 325852 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8578. Min Act: -0.1700
Data Index: 3941526 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8578. Min Act: -0.1700
Data Index: 8308222 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4203. Min Range: -5.4203
Max Act: 4.8890. Min Act: -0.1700
Data Index: 8776600 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19