Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 3881810 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.5550. Min Act: -0.1700
Data Index: 3881812 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.3363. Min Act: -0.1700
Data Index: 601750 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.3050. Min Act: -0.1700
Data Index: 601743 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.2738. Min Act: -0.1700
Data Index: 5673074 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.2425. Min Act: -0.1700
Data Index: 7979042 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.2425. Min Act: -0.1700
Data Index: 8245891 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.1800. Min Act: -0.1700
Data Index: 7020173 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.1488. Min Act: -0.1700
Data Index: 5669142 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.1488. Min Act: -0.1700
Data Index: 4837286 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.0550. Min Act: -0.1700
Data Index: 2868177 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5550. Min Range: -5.5550
Max Act: 5.0238. Min Act: -0.1700
Data Index: 5673075 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.9925. Min Act: -0.1700
Data Index: 7714758 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.9925. Min Act: -0.1700
Data Index: 2071178 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.9613. Min Act: -0.1700
Data Index: 5669141 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.9300. Min Act: -0.1700
Data Index: 1108570 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.9300. Min Act: -0.1700
Data Index: 6210218 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.8988. Min Act: -0.1700
Data Index: 2791277 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.8675. Min Act: -0.1700
Data Index: 5052855 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5550. Min Range: -5.5550
Max Act: 4.8363. Min Act: -0.1700
Data Index: 5525811 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19