Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.3465. Min Act: -0.1700
Data Index: 7058291 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.2215. Min Act: -0.1700
Data Index: 1073216 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.1277. Min Act: -0.1700
Data Index: 883734 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.0965. Min Act: -0.1700
Data Index: 4334078 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.0965. Min Act: -0.1700
Data Index: 6477714 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3465. Min Range: -7.3465
Max Act: 7.0027. Min Act: -0.1700
Data Index: 7058290 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9402. Min Act: -0.1700
Data Index: 3684627 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 1162621 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 8764316 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 6870655 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 7660907 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 1735340 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.9090. Min Act: -0.1700
Data Index: 6939548 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8777. Min Act: -0.1700
Data Index: 7191690 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8465. Min Act: -0.1700
Data Index: 1144025 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8777. Min Act: -0.1700
Data Index: 26505 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8465. Min Act: -0.1700
Data Index: 957950 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8465. Min Act: -0.1700
Data Index: 6060319 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.7840. Min Act: -0.1700
Data Index: 996100 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3465. Min Range: -7.3465
Max Act: 6.8152. Min Act: -0.1700
Data Index: 2425248 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19