Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.7559. Min Act: -0.1700
Data Index: 5460138 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.5684. Min Act: -0.1700
Data Index: 57307 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.5371. Min Act: -0.1700
Data Index: 8324236 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.4121. Min Act: -0.1700
Data Index: 6220418 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.3809. Min Act: -0.1700
Data Index: 3385027 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.3496. Min Act: -0.1700
Data Index: 8037151 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.3496. Min Act: -0.1700
Data Index: 105102 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.3184. Min Act: -0.1700
Data Index: 5437161 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.2559. Min Act: -0.1700
Data Index: 6446876 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.2559. Min Act: -0.1700
Data Index: 6060934 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.2559. Min Act: -0.1700
Data Index: 5361001 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1934. Min Act: -0.1700
Data Index: 3272752 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.2246. Min Act: -0.1700
Data Index: 5439585 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1934. Min Act: -0.1700
Data Index: 2042933 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1621. Min Act: -0.1700
Data Index: 3086739 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1934. Min Act: -0.1700
Data Index: 5055463 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1934. Min Act: -0.1700
Data Index: 3852501 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1621. Min Act: -0.1700
Data Index: 2854587 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1621. Min Act: -0.1700
Data Index: 2712104 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7559. Min Range: -6.7559
Max Act: 6.1621. Min Act: -0.1700
Data Index: 543920 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19