Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 240 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1231. Min Range: -9.1231
Max Act: 9.1231. Min Act: -0.1700
Data Index: 7663738 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.8106. Min Act: -0.1700
Data Index: 6046914 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.6856. Min Act: -0.1700
Data Index: 5800979 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.6231. Min Act: -0.1700
Data Index: 8559296 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.6231. Min Act: -0.1700
Data Index: 959868 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4981. Min Act: -0.1700
Data Index: 4808303 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4981. Min Act: -0.1700
Data Index: 5961274 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4981. Min Act: -0.1700
Data Index: 8661625 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4356. Min Act: -0.1700
Data Index: 195694 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4356. Min Act: -0.1700
Data Index: 4376735 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.4356. Min Act: -0.1700
Data Index: 3004560 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3731. Min Act: -0.1700
Data Index: 7764734 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 3361154 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 5961277 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 8559297 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 1585734 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 4031050 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.3106. Min Act: -0.1700
Data Index: 4902028 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.2481. Min Act: -0.1700
Data Index: 2101132 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1231. Min Range: -9.1231
Max Act: 8.2481. Min Act: -0.1700
Data Index: 4523297 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19