Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1139. Min Range: -6.1139
Max Act: 6.1139. Min Act: -0.1700
Data Index: 1821294 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 5515759 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 3090560 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.9264. Min Act: -0.1700
Data Index: 6351309 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.9264. Min Act: -0.1700
Data Index: 338076 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.8639. Min Act: -0.1700
Data Index: 338072 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.8327. Min Act: -0.1700
Data Index: 338073 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.8327. Min Act: -0.1700
Data Index: 5781248 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3586844 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.7077. Min Act: -0.1700
Data Index: 8176291 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.7077. Min Act: -0.1700
Data Index: 1236676 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 2968575 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6764. Min Act: -0.1700
Data Index: 3026117 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 3614124 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 3210567 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 442104 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 1356728 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6452. Min Act: -0.1700
Data Index: 4987979 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1449862 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1139. Min Range: -6.1139
Max Act: 5.6139. Min Act: -0.1700
Data Index: 4496356 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19