Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1500 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3055. Min Range: -4.3055
Max Act: 4.3055. Min Act: -0.1700
Data Index: 4142016 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3055. Min Range: -4.3055
Max Act: 4.1180. Min Act: -0.1700
Data Index: 3916943 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.9617. Min Act: -0.1700
Data Index: 6352491 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.9304. Min Act: -0.1700
Data Index: 6210017 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.9304. Min Act: -0.1700
Data Index: 2329254 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.8992. Min Act: -0.1700
Data Index: 8108049 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.9304. Min Act: -0.1700
Data Index: 4567291 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.8366. Min Act: -0.1700
Data Index: 7976034 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.8523. Min Act: -0.1700
Data Index: 4306753 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.8366. Min Act: -0.1700
Data Index: 4068132 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.8210. Min Act: -0.1700
Data Index: 7879533 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7897. Min Act: -0.1700
Data Index: 7907451 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7897. Min Act: -0.1700
Data Index: 3415902 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7897. Min Act: -0.1700
Data Index: 3278285 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7897. Min Act: -0.1700
Data Index: 8189338 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7897. Min Act: -0.1700
Data Index: 1163094 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7741. Min Act: -0.1700
Data Index: 2549664 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7741. Min Act: -0.1700
Data Index: 4616802 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7741. Min Act: -0.1700
Data Index: 4725702 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3055. Min Range: -4.3055
Max Act: 3.7584. Min Act: -0.1700
Data Index: 189354 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19