Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.1223. Min Act: -0.1700
Data Index: 7268919 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.1223. Min Act: -0.1700
Data Index: 5723581 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0434. Min Act: -0.1700
Data Index: 7469959 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0276. Min Act: -0.1700
Data Index: 699171 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0276. Min Act: -0.1700
Data Index: 6508183 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0118. Min Act: -0.1700
Data Index: 1283288 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0118. Min Act: -0.1700
Data Index: 3162270 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0276. Min Act: -0.1700
Data Index: 6252699 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9960. Min Act: -0.1700
Data Index: 5384854 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1223. Min Range: -3.1223
Max Act: 3.0118. Min Act: -0.1700
Data Index: 5118723 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9960. Min Act: -0.1700
Data Index: 8115421 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9960. Min Act: -0.1700
Data Index: 398892 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9960. Min Act: -0.1700
Data Index: 3912357 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9802. Min Act: -0.1700
Data Index: 2745799 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9802. Min Act: -0.1700
Data Index: 8476351 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9802. Min Act: -0.1700
Data Index: 2545996 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9802. Min Act: -0.1700
Data Index: 2546499 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9802. Min Act: -0.1700
Data Index: 7812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9644. Min Act: -0.1700
Data Index: 5685522 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1223. Min Range: -3.1223
Max Act: 2.9644. Min Act: -0.1700
Data Index: 7201072 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19