Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.6258. Min Act: -0.1700
Data Index: 3667014 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.4383. Min Act: -0.1700
Data Index: 7268015 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.3758. Min Act: -0.1700
Data Index: 1399575 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.1571. Min Act: -0.1700
Data Index: 43728 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0946. Min Act: -0.1700
Data Index: 341898 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0633. Min Act: -0.1700
Data Index: 5680877 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0321. Min Act: -0.1700
Data Index: 144146 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0008. Min Act: -0.1700
Data Index: 7174009 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0321. Min Act: -0.1700
Data Index: 8623173 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6258. Min Range: -7.6258
Max Act: 7.0008. Min Act: -0.1700
Data Index: 7179269 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.9696. Min Act: -0.1700
Data Index: 26810 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.9071. Min Act: -0.1700
Data Index: 3224367 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.8133. Min Act: -0.1700
Data Index: 8034927 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.8133. Min Act: -0.1700
Data Index: 1709890 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.8133. Min Act: -0.1700
Data Index: 1790042 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.8446. Min Act: -0.1700
Data Index: 5982875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.7821. Min Act: -0.1700
Data Index: 116045 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.7821. Min Act: -0.1700
Data Index: 3809977 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.7508. Min Act: -0.1700
Data Index: 7301650 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6258. Min Range: -7.6258
Max Act: 6.7508. Min Act: -0.1700
Data Index: 6915891 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19