Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0263. Min Range: -5.0263
Max Act: 5.0263. Min Act: -0.1700
Data Index: 2443002 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.9325. Min Act: -0.1700
Data Index: 2164848 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.9325. Min Act: -0.1700
Data Index: 448159 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.9013. Min Act: -0.1700
Data Index: 870426 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8700. Min Act: -0.1700
Data Index: 2404425 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8700. Min Act: -0.1700
Data Index: 7654497 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8700. Min Act: -0.1700
Data Index: 250712 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8388. Min Act: -0.1700
Data Index: 5359361 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 1720389 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 7076305 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 8079835 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 7962115 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 5652173 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.8075. Min Act: -0.1700
Data Index: 1951222 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7763. Min Act: -0.1700
Data Index: 3374442 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7763. Min Act: -0.1700
Data Index: 353230 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7763. Min Act: -0.1700
Data Index: 3759346 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7763. Min Act: -0.1700
Data Index: 1541665 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7450. Min Act: -0.1700
Data Index: 946833 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0263. Min Range: -5.0263
Max Act: 4.7138. Min Act: -0.1700
Data Index: 2951140 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19