Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1189. Min Range: -7.1189
Max Act: 7.1189. Min Act: -0.1700
Data Index: 2000390 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.7127. Min Act: -0.1700
Data Index: 2442653 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.4627. Min Act: -0.1700
Data Index: 5915110 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.4314. Min Act: -0.1700
Data Index: 5430044 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.3377. Min Act: -0.1700
Data Index: 6516439 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.2752. Min Act: -0.1700
Data Index: 6705244 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.2752. Min Act: -0.1700
Data Index: 888074 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.2127. Min Act: -0.1700
Data Index: 5069805 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.1814. Min Act: -0.1700
Data Index: 6767263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.1189. Min Act: -0.1700
Data Index: 6657712 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.1502. Min Act: -0.1700
Data Index: 4790540 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0877. Min Act: -0.1700
Data Index: 5272890 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0877. Min Act: -0.1700
Data Index: 3319729 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0564. Min Act: -0.1700
Data Index: 3592121 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0564. Min Act: -0.1700
Data Index: 7220534 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0564. Min Act: -0.1700
Data Index: 167810 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0252. Min Act: -0.1700
Data Index: 2206233 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0252. Min Act: -0.1700
Data Index: 2192471 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1189. Min Range: -7.1189
Max Act: 6.0252. Min Act: -0.1700
Data Index: 895216 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1189. Min Range: -7.1189
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4627364 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19