Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.6288. Min Act: -0.1700
Data Index: 8594385 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.5351. Min Act: -0.1700
Data Index: 3204628 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.5038. Min Act: -0.1700
Data Index: 3077038 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.4101. Min Act: -0.1700
Data Index: 2828764 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.3476. Min Act: -0.1700
Data Index: 7182209 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.2851. Min Act: -0.1700
Data Index: 2772821 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.0663. Min Act: -0.1700
Data Index: 1385255 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.0351. Min Act: -0.1700
Data Index: 2505239 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.0038. Min Act: -0.1700
Data Index: 6067718 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1466070 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6288. Min Range: -6.6288
Max Act: 6.0038. Min Act: -0.1700
Data Index: 5962434 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9726. Min Act: -0.1700
Data Index: 8123995 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9726. Min Act: -0.1700
Data Index: 8271474 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9726. Min Act: -0.1700
Data Index: 4640418 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 5292222 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 8064424 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 4425392 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9101. Min Act: -0.1700
Data Index: 594964 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9726. Min Act: -0.1700
Data Index: 226437 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6288. Min Range: -6.6288
Max Act: 5.9413. Min Act: -0.1700
Data Index: 7853432 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19