Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6146 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.2214. Min Act: -0.1700
Data Index: 624450 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.1589. Min Act: -0.1700
Data Index: 1652530 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.1276. Min Act: -0.1700
Data Index: 6052517 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2214. Min Range: -4.2214
Max Act: 4.0964. Min Act: -0.1700
Data Index: 1762169 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.9713. Min Act: -0.1700
Data Index: 7841085 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.9401. Min Act: -0.1700
Data Index: 3854904 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.9088. Min Act: -0.1700
Data Index: 7438806 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8463. Min Act: -0.1700
Data Index: 4808556 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8775. Min Act: -0.1700
Data Index: 2053837 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8775. Min Act: -0.1700
Data Index: 6261160 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8775. Min Act: -0.1700
Data Index: 2706536 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.9088. Min Act: -0.1700
Data Index: 7830124 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8775. Min Act: -0.1700
Data Index: 8174245 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8463. Min Act: -0.1700
Data Index: 3661828 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8463. Min Act: -0.1700
Data Index: 4905107 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8463. Min Act: -0.1700
Data Index: 5278088 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8463. Min Act: -0.1700
Data Index: 6123400 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8150. Min Act: -0.1700
Data Index: 6704082 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8150. Min Act: -0.1700
Data Index: 4817004 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2214. Min Range: -4.2214
Max Act: 3.8150. Min Act: -0.1700
Data Index: 6781065 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19