Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.3319. Min Act: -0.1700
Data Index: 435651 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.3319. Min Act: -0.1700
Data Index: 2821107 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.2069. Min Act: -0.1700
Data Index: 3766831 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.2069. Min Act: -0.1700
Data Index: 8038282 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.2069. Min Act: -0.1700
Data Index: 4483890 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.0819. Min Act: -0.1700
Data Index: 6085331 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.0819. Min Act: -0.1700
Data Index: 2588016 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.0194. Min Act: -0.1700
Data Index: 5938098 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3319. Min Range: -9.3319
Max Act: 9.0194. Min Act: -0.1700
Data Index: 7837029 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.9569. Min Act: -0.1700
Data Index: 1502946 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.9569. Min Act: -0.1700
Data Index: 494708 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.9569. Min Act: -0.1700
Data Index: 4615043 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.8944. Min Act: -0.1700
Data Index: 1180910 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.8944. Min Act: -0.1700
Data Index: 5999966 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.8319. Min Act: -0.1700
Data Index: 6919967 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.8319. Min Act: -0.1700
Data Index: 4274133 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.8319. Min Act: -0.1700
Data Index: 7877116 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.7694. Min Act: -0.1700
Data Index: 8801117 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.7694. Min Act: -0.1700
Data Index: 3984329 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3319. Min Range: -9.3319
Max Act: 8.7069. Min Act: -0.1700
Data Index: 5672798 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19