Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1210. Min Range: -6.1210
Max Act: 6.1210. Min Act: -0.1700
Data Index: 4669902 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1210. Min Range: -6.1210
Max Act: 6.0585. Min Act: -0.1700
Data Index: 817355 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1210. Min Range: -6.1210
Max Act: 6.0585. Min Act: -0.1700
Data Index: 5061989 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.9960. Min Act: -0.1700
Data Index: 7935858 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4387489 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.9022. Min Act: -0.1700
Data Index: 644959 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.8397. Min Act: -0.1700
Data Index: 7668670 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.8710. Min Act: -0.1700
Data Index: 2887575 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.8085. Min Act: -0.1700
Data Index: 7041081 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.8085. Min Act: -0.1700
Data Index: 6479831 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.8085. Min Act: -0.1700
Data Index: 2476153 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.7460. Min Act: -0.1700
Data Index: 8788220 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6490165 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.6522. Min Act: -0.1700
Data Index: 1850055 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.5897. Min Act: -0.1700
Data Index: 511956 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.5897. Min Act: -0.1700
Data Index: 1055685 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.4960. Min Act: -0.1700
Data Index: 6858315 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.5272. Min Act: -0.1700
Data Index: 7539280 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.5272. Min Act: -0.1700
Data Index: 1361324 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1210. Min Range: -6.1210
Max Act: 5.5272. Min Act: -0.1700
Data Index: 6869234 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19