Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0873. Min Range: -8.0873
Max Act: 8.0873. Min Act: -0.1700
Data Index: 5574029 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0873. Min Range: -8.0873
Max Act: 8.0873. Min Act: -0.1700
Data Index: 5574031 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.9935. Min Act: -0.1700
Data Index: 115172 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.9623. Min Act: -0.1700
Data Index: 115166 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.8998. Min Act: -0.1700
Data Index: 3098755 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.8060. Min Act: -0.1700
Data Index: 2164486 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.8060. Min Act: -0.1700
Data Index: 6438499 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.8060. Min Act: -0.1700
Data Index: 7714458 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.8060. Min Act: -0.1700
Data Index: 8428062 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.7748. Min Act: -0.1700
Data Index: 1893567 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.7435. Min Act: -0.1700
Data Index: 1945669 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.7123. Min Act: -0.1700
Data Index: 6811419 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.7435. Min Act: -0.1700
Data Index: 1795322 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.7123. Min Act: -0.1700
Data Index: 4449170 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.6498. Min Act: -0.1700
Data Index: 5434193 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.6810. Min Act: -0.1700
Data Index: 6400001 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.6498. Min Act: -0.1700
Data Index: 4876941 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.6498. Min Act: -0.1700
Data Index: 6694327 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.6498. Min Act: -0.1700
Data Index: 1804687 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0873. Min Range: -8.0873
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1412525 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19