Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3803. Min Range: -7.3803
Max Act: 7.3803. Min Act: -0.1700
Data Index: 6234074 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3803. Min Range: -7.3803
Max Act: 7.2866. Min Act: -0.1700
Data Index: 7239105 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3803. Min Range: -7.3803
Max Act: 7.0678. Min Act: -0.1700
Data Index: 5860773 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.8178. Min Act: -0.1700
Data Index: 6264992 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.8178. Min Act: -0.1700
Data Index: 1932457 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.7553. Min Act: -0.1700
Data Index: 5485253 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.7241. Min Act: -0.1700
Data Index: 3498562 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.6616. Min Act: -0.1700
Data Index: 1753346 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.6616. Min Act: -0.1700
Data Index: 2500747 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5678. Min Act: -0.1700
Data Index: 5099343 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4284667 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5366. Min Act: -0.1700
Data Index: 4528635 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5366. Min Act: -0.1700
Data Index: 986531 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5053. Min Act: -0.1700
Data Index: 3797135 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.5053. Min Act: -0.1700
Data Index: 7826743 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.4741. Min Act: -0.1700
Data Index: 5656498 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.4741. Min Act: -0.1700
Data Index: 2344299 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.4741. Min Act: -0.1700
Data Index: 3314765 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.4741. Min Act: -0.1700
Data Index: 5399032 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3803. Min Range: -7.3803
Max Act: 6.4741. Min Act: -0.1700
Data Index: 8126949 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19