Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2893. Min Range: -6.2893
Max Act: 6.2893. Min Act: -0.1700
Data Index: 5321352 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.8518. Min Act: -0.1700
Data Index: 13940 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.8518. Min Act: -0.1700
Data Index: 2913178 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.8205. Min Act: -0.1700
Data Index: 7434495 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.8205. Min Act: -0.1700
Data Index: 3505341 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6655054 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 2749444 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6955. Min Act: -0.1700
Data Index: 5366134 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4019112 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6955. Min Act: -0.1700
Data Index: 2383326 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 4795301 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 3211434 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6330. Min Act: -0.1700
Data Index: 4268524 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6330. Min Act: -0.1700
Data Index: 3794577 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6643. Min Act: -0.1700
Data Index: 5897548 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6018. Min Act: -0.1700
Data Index: 3606835 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6018. Min Act: -0.1700
Data Index: 4005969 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6018. Min Act: -0.1700
Data Index: 2563163 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6018. Min Act: -0.1700
Data Index: 8012356 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2893. Min Range: -6.2893
Max Act: 5.6018. Min Act: -0.1700
Data Index: 5602645 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19