Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.4461. Min Act: -0.1700
Data Index: 7966116 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.3836. Min Act: -0.1700
Data Index: 4173457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.2586. Min Act: -0.1700
Data Index: 1460291 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.2586. Min Act: -0.1700
Data Index: 5846396 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.2586. Min Act: -0.1700
Data Index: 2820386 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1961. Min Act: -0.1700
Data Index: 7244766 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4690822 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4473837 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 7579738 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2134077 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 7141535 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 1039400 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3919154 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1023. Min Act: -0.1700
Data Index: 1513924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5682152 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3504033 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1023. Min Act: -0.1700
Data Index: 1395740 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.1336. Min Act: -0.1700
Data Index: 7226637 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.0711. Min Act: -0.1700
Data Index: 6498745 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4461. Min Range: -5.4461
Max Act: 5.0711. Min Act: -0.1700
Data Index: 3824226 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19