Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.3247. Min Act: -0.1700
Data Index: 7719855 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.1372. Min Act: -0.1700
Data Index: 6462524 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.1060. Min Act: -0.1700
Data Index: 1888977 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.0747. Min Act: -0.1700
Data Index: 6659402 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.0435. Min Act: -0.1700
Data Index: 8250054 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3247. Min Range: -7.3247
Max Act: 7.0122. Min Act: -0.1700
Data Index: 7055582 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9185. Min Act: -0.1700
Data Index: 377429 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.9185. Min Act: -0.1700
Data Index: 7335545 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8560. Min Act: -0.1700
Data Index: 5084683 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8247. Min Act: -0.1700
Data Index: 8028425 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.8247. Min Act: -0.1700
Data Index: 2675070 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7935. Min Act: -0.1700
Data Index: 3360337 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7935. Min Act: -0.1700
Data Index: 5979373 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7935. Min Act: -0.1700
Data Index: 1201375 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7935. Min Act: -0.1700
Data Index: 1159131 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7622. Min Act: -0.1700
Data Index: 4870685 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5628132 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7310. Min Act: -0.1700
Data Index: 3895729 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.6997. Min Act: -0.1700
Data Index: 7385475 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3247. Min Range: -7.3247
Max Act: 6.7310. Min Act: -0.1700
Data Index: 2503173 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19