Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0100. Min Range: -5.0100
Max Act: 5.0100. Min Act: -0.1700
Data Index: 8373909 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.9475. Min Act: -0.1700
Data Index: 2350053 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.9475. Min Act: -0.1700
Data Index: 3002560 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4771724 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8850. Min Act: -0.1700
Data Index: 3357300 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8850. Min Act: -0.1700
Data Index: 8063803 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3357291 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3357286 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3357295 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8225. Min Act: -0.1700
Data Index: 8388645 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8225. Min Act: -0.1700
Data Index: 8388646 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.8225. Min Act: -0.1700
Data Index: 7647657 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7912. Min Act: -0.1700
Data Index: 8388636 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7912. Min Act: -0.1700
Data Index: 4492551 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7600. Min Act: -0.1700
Data Index: 210580 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7600. Min Act: -0.1700
Data Index: 4075301 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7600. Min Act: -0.1700
Data Index: 3357299 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7600. Min Act: -0.1700
Data Index: 3357296 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7287. Min Act: -0.1700
Data Index: 7681405 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0100. Min Range: -5.0100
Max Act: 4.7287. Min Act: -0.1700
Data Index: 3357293 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19