Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.3134. Min Act: -0.1700
Data Index: 2335913 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.3134. Min Act: -0.1700
Data Index: 4293703 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.2197. Min Act: -0.1700
Data Index: 8399475 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.1571. Min Act: -0.1700
Data Index: 1766562 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.1571. Min Act: -0.1700
Data Index: 3804575 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.1259. Min Act: -0.1700
Data Index: 4280709 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.1259. Min Act: -0.1700
Data Index: 4674708 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.0946. Min Act: -0.1700
Data Index: 3904681 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.0009. Min Act: -0.1700
Data Index: 5803628 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.0009. Min Act: -0.1700
Data Index: 2355906 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.0009. Min Act: -0.1700
Data Index: 4936514 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3134. Min Range: -4.3134
Max Act: 4.0009. Min Act: -0.1700
Data Index: 7837083 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9696. Min Act: -0.1700
Data Index: 8106539 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9696. Min Act: -0.1700
Data Index: 8080056 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 425431 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 981002 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 578349 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 8662732 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 2490542 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3134. Min Range: -4.3134
Max Act: 3.9383. Min Act: -0.1700
Data Index: 2394981 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19