Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0157. Min Range: -6.0157
Max Act: 6.0157. Min Act: -0.1700
Data Index: 8395598 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.8595. Min Act: -0.1700
Data Index: 7585469 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.7657. Min Act: -0.1700
Data Index: 5817027 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.7970. Min Act: -0.1700
Data Index: 5817016 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.6720. Min Act: -0.1700
Data Index: 7342971 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.6407. Min Act: -0.1700
Data Index: 6061191 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3889170 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.6095. Min Act: -0.1700
Data Index: 5180691 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.6095. Min Act: -0.1700
Data Index: 7730920 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.5470. Min Act: -0.1700
Data Index: 7342968 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.5470. Min Act: -0.1700
Data Index: 1046857 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.5157. Min Act: -0.1700
Data Index: 5817025 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.5157. Min Act: -0.1700
Data Index: 5817020 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4845. Min Act: -0.1700
Data Index: 8395591 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4845. Min Act: -0.1700
Data Index: 7342975 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4845. Min Act: -0.1700
Data Index: 5180696 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4845. Min Act: -0.1700
Data Index: 5817012 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4532. Min Act: -0.1700
Data Index: 3938954 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4220. Min Act: -0.1700
Data Index: 7342964 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0157. Min Range: -6.0157
Max Act: 5.4532. Min Act: -0.1700
Data Index: 846933 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19