Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.5356. Min Act: -0.1700
Data Index: 2813624 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3168. Min Act: -0.1700
Data Index: 763541 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2856. Min Act: -0.1700
Data Index: 1508756 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2856. Min Act: -0.1700
Data Index: 2533049 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1330927 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1961068 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 340524 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 6552607 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0668. Min Act: -0.1700
Data Index: 8330534 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 1626497 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0668. Min Act: -0.1700
Data Index: 7739560 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0356. Min Act: -0.1700
Data Index: 5179621 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0668. Min Act: -0.1700
Data Index: 4606932 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0043. Min Act: -0.1700
Data Index: 6026825 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0043. Min Act: -0.1700
Data Index: 5127420 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0043. Min Act: -0.1700
Data Index: 8632850 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.9106. Min Act: -0.1700
Data Index: 6481167 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.8481. Min Act: -0.1700
Data Index: 6937049 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.8793. Min Act: -0.1700
Data Index: 2803306 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5356. Min Range: -6.5356
Max Act: 5.8793. Min Act: -0.1700
Data Index: 3450677 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19