Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4385 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2865. Min Range: -7.2865
Max Act: 7.2865. Min Act: -0.1700
Data Index: 8601810 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2865. Min Range: -7.2865
Max Act: 7.2552. Min Act: -0.1700
Data Index: 3090217 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2865. Min Range: -7.2865
Max Act: 7.0365. Min Act: -0.1700
Data Index: 355328 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2865. Min Range: -7.2865
Max Act: 7.0052. Min Act: -0.1700
Data Index: 1684524 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2865. Min Range: -7.2865
Max Act: 7.0052. Min Act: -0.1700
Data Index: 1822255 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.9740. Min Act: -0.1700
Data Index: 695908 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.9427. Min Act: -0.1700
Data Index: 4964980 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.9115. Min Act: -0.1700
Data Index: 3864199 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8802. Min Act: -0.1700
Data Index: 8126070 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8802. Min Act: -0.1700
Data Index: 2732172 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8802. Min Act: -0.1700
Data Index: 433402 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8802. Min Act: -0.1700
Data Index: 2684643 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8490. Min Act: -0.1700
Data Index: 4693356 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8490. Min Act: -0.1700
Data Index: 4099810 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8490. Min Act: -0.1700
Data Index: 8021190 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8490. Min Act: -0.1700
Data Index: 8477212 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8177. Min Act: -0.1700
Data Index: 1370536 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8177. Min Act: -0.1700
Data Index: 3502166 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.8177. Min Act: -0.1700
Data Index: 4606773 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2865. Min Range: -7.2865
Max Act: 6.7865. Min Act: -0.1700
Data Index: 7320160 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19