Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.3530. Min Act: -0.1700
Data Index: 82059 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.2905. Min Act: -0.1700
Data Index: 3252372 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.2593. Min Act: -0.1700
Data Index: 5827174 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1968. Min Act: -0.1700
Data Index: 4722465 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1655. Min Act: -0.1700
Data Index: 3252373 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1968. Min Act: -0.1700
Data Index: 2725401 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1968. Min Act: -0.1700
Data Index: 6803735 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1699
Data Index: 3421502 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1655. Min Act: -0.1700
Data Index: 6773088 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 689592 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1655. Min Act: -0.1700
Data Index: 2434520 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1655. Min Act: -0.1699
Data Index: 6666517 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 1601888 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1699
Data Index: 6331402 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 2725418 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7822155 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1699
Data Index: 1499303 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 2434515 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.1343. Min Act: -0.1700
Data Index: 8070900 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3530. Min Range: -6.3530
Max Act: 6.0718. Min Act: -0.1699
Data Index: 3252369 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19