Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5991 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1275. Min Range: -6.1275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 4554690 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.9088. Min Act: -0.1700
Data Index: 6275362 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.7525. Min Act: -0.1700
Data Index: 1613910 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.6900. Min Act: -0.1700
Data Index: 916101 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.6900. Min Act: -0.1700
Data Index: 2067976 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.6275. Min Act: -0.1700
Data Index: 3945241 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.6275. Min Act: -0.1700
Data Index: 1800406 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5963. Min Act: -0.1700
Data Index: 2513246 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 1272302 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 7578337 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 534113 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 1658741 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 522499 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 5954624 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5338. Min Act: -0.1700
Data Index: 6505118 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5338. Min Act: -0.1700
Data Index: 3549651 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5025. Min Act: -0.1700
Data Index: 1141957 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5025. Min Act: -0.1700
Data Index: 8115899 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5025. Min Act: -0.1700
Data Index: 5880246 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1275. Min Range: -6.1275
Max Act: 5.5025. Min Act: -0.1700
Data Index: 3634630 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19