Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.3211. Min Act: -0.1700
Data Index: 4443577 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3726200 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2335154 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1961. Min Act: -0.1700
Data Index: 769625 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2228138 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1336. Min Act: -0.1700
Data Index: 1926474 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1336. Min Act: -0.1700
Data Index: 4011155 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1023. Min Act: -0.1700
Data Index: 4011149 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.1023. Min Act: -0.1700
Data Index: 2772312 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0711. Min Act: -0.1700
Data Index: 3020429 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0711. Min Act: -0.1700
Data Index: 1926473 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0398. Min Act: -0.1700
Data Index: 1826598 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0711. Min Act: -0.1700
Data Index: 3682333 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0398. Min Act: -0.1700
Data Index: 36471 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0398. Min Act: -0.1700
Data Index: 2819053 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0398. Min Act: -0.1700
Data Index: 6887428 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0398. Min Act: -0.1700
Data Index: 2317929 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0086. Min Act: -0.1700
Data Index: 4670285 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0086. Min Act: -0.1700
Data Index: 5763080 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3211. Min Range: -5.3211
Max Act: 5.0086. Min Act: -0.1700
Data Index: 5110468 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19