Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 2978198 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 2393382 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3140. Min Act: -0.1700
Data Index: 2599400 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2828. Min Act: -0.1700
Data Index: 3155828 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 6551599 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2203. Min Act: -0.1700
Data Index: 374800 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2203. Min Act: -0.1700
Data Index: 3371909 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 6560832 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2091691 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 1028189 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 3972067 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 158354 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2766684 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 158352 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 5712543 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5174740 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 2120666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 8323200 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3036642 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6954822 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19