Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.4854. Min Act: -0.1700
Data Index: 8328670 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.3291. Min Act: -0.1700
Data Index: 2223544 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.3291. Min Act: -0.1700
Data Index: 5980692 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2979. Min Act: -0.1700
Data Index: 5210021 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2979. Min Act: -0.1700
Data Index: 7397595 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2979. Min Act: -0.1700
Data Index: 5904702 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2354. Min Act: -0.1700
Data Index: 4173355 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.1729. Min Act: -0.1700
Data Index: 7456029 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2041. Min Act: -0.1700
Data Index: 6327682 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.1729. Min Act: -0.1700
Data Index: 5280552 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.2041. Min Act: -0.1700
Data Index: 738670 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.1416. Min Act: -0.1700
Data Index: 7752690 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.1104. Min Act: -0.1700
Data Index: 4583879 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0791. Min Act: -0.1700
Data Index: 5618258 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0479. Min Act: -0.1700
Data Index: 5566454 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0479. Min Act: -0.1700
Data Index: 2420614 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0166. Min Act: -0.1700
Data Index: 5820086 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0166. Min Act: -0.1700
Data Index: 1225446 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4854. Min Range: -7.4854
Max Act: 6.9854. Min Act: -0.1700
Data Index: 6401636 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4854. Min Range: -7.4854
Max Act: 7.0166. Min Act: -0.1700
Data Index: 543478 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19