Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 682 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8669. Min Act: -0.1700
Data Index: 8218507 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8669. Min Act: -0.1700
Data Index: 4654420 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8669. Min Act: -0.1700
Data Index: 3645013 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8669. Min Act: -0.1700
Data Index: 3281400 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8356. Min Act: -0.1700
Data Index: 2159076 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8356. Min Act: -0.1700
Data Index: 3745290 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8356. Min Act: -0.1700
Data Index: 3382040 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8669. Min Act: -0.1700
Data Index: 7586637 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8356. Min Act: -0.1700
Data Index: 6481278 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8044. Min Act: -0.1700
Data Index: 7125050 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8044. Min Act: -0.1700
Data Index: 2641819 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8356. Min Act: -0.1700
Data Index: 1277267 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8044. Min Act: -0.1700
Data Index: 5842674 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.8044. Min Act: -0.1700
Data Index: 7668639 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7731. Min Act: -0.1700
Data Index: 5550259 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7731. Min Act: -0.1700
Data Index: 3415919 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7731. Min Act: -0.1700
Data Index: 7634785 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4195456 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7419. Min Act: -0.1700
Data Index: 87751 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8669. Min Range: -4.8669
Max Act: 4.7731. Min Act: -0.1700
Data Index: 5755924 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19