Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.6695. Min Act: -0.1700
Data Index: 618416 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.6695. Min Act: -0.1700
Data Index: 88652 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.6070. Min Act: -0.1700
Data Index: 1399289 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.6382. Min Act: -0.1700
Data Index: 2045194 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.5445. Min Act: -0.1700
Data Index: 618414 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.5445. Min Act: -0.1700
Data Index: 2586317 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5095531 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.3882. Min Act: -0.1700
Data Index: 2428322 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.3882. Min Act: -0.1700
Data Index: 848462 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.3257. Min Act: -0.1700
Data Index: 5095528 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.3257. Min Act: -0.1700
Data Index: 3109320 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.3257. Min Act: -0.1700
Data Index: 7472182 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2945. Min Act: -0.1700
Data Index: 2045199 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2632. Min Act: -0.1700
Data Index: 7937414 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2632. Min Act: -0.1700
Data Index: 4677324 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2632. Min Act: -0.1700
Data Index: 1688990 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2632. Min Act: -0.1700
Data Index: 5787747 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2632. Min Act: -0.1700
Data Index: 1655530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.2320. Min Act: -0.1700
Data Index: 933752 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6695. Min Range: -5.6695
Max Act: 5.1695. Min Act: -0.1700
Data Index: 1309108 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19