Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.3206. Min Act: -0.1700
Data Index: 2233559 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.1643. Min Act: -0.1700
Data Index: 7873121 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.1331. Min Act: -0.1700
Data Index: 3682443 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.1331. Min Act: -0.1700
Data Index: 6830722 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.1018. Min Act: -0.1700
Data Index: 7570799 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0393. Min Act: -0.1700
Data Index: 1708572 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0393. Min Act: -0.1700
Data Index: 7732160 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0081. Min Act: -0.1700
Data Index: 3261948 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9768. Min Act: -0.1700
Data Index: 3790311 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3206. Min Range: -6.3206
Max Act: 6.0081. Min Act: -0.1700
Data Index: 4412317 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9456. Min Act: -0.1700
Data Index: 8732013 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9143. Min Act: -0.1700
Data Index: 6533482 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9456. Min Act: -0.1700
Data Index: 7891018 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9456. Min Act: -0.1700
Data Index: 2146392 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9143. Min Act: -0.1700
Data Index: 2549327 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.9143. Min Act: -0.1700
Data Index: 521881 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8518. Min Act: -0.1700
Data Index: 6901907 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8518. Min Act: -0.1700
Data Index: 4414238 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8518. Min Act: -0.1700
Data Index: 3648299 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3206. Min Range: -6.3206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 8261731 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19