Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1170. Min Range: -7.1170
Max Act: 7.1170. Min Act: -0.1700
Data Index: 8266755 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.5233. Min Act: -0.1700
Data Index: 1909901 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.3358. Min Act: -0.1700
Data Index: 2081247 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.3358. Min Act: -0.1700
Data Index: 6345457 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2659083 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.3045. Min Act: -0.1700
Data Index: 4675551 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.2733. Min Act: -0.1700
Data Index: 8761478 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.2108. Min Act: -0.1700
Data Index: 6697430 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1334299 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.1795. Min Act: -0.1700
Data Index: 376964 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0858. Min Act: -0.1700
Data Index: 6562736 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2533943 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0858. Min Act: -0.1700
Data Index: 654463 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0545. Min Act: -0.1700
Data Index: 2515616 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0545. Min Act: -0.1700
Data Index: 3155441 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0858. Min Act: -0.1700
Data Index: 6467508 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0233. Min Act: -0.1700
Data Index: 300672 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0545. Min Act: -0.1700
Data Index: 4352246 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0233. Min Act: -0.1700
Data Index: 7644428 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1170. Min Range: -7.1170
Max Act: 6.0233. Min Act: -0.1700
Data Index: 8027618 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19