Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.1783. Min Act: -0.1700
Data Index: 4776191 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.2408. Min Act: -0.1700
Data Index: 8491359 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.0845. Min Act: -0.1700
Data Index: 1836719 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.0533. Min Act: -0.1700
Data Index: 8639877 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.1158. Min Act: -0.1700
Data Index: 3402167 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.0533. Min Act: -0.1700
Data Index: 5657784 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2408. Min Range: -7.2408
Max Act: 7.0533. Min Act: -0.1700
Data Index: 7247315 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.9595. Min Act: -0.1700
Data Index: 7906860 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8658. Min Act: -0.1700
Data Index: 910313 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8658. Min Act: -0.1700
Data Index: 4087554 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8658. Min Act: -0.1700
Data Index: 7490085 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8658. Min Act: -0.1700
Data Index: 8501053 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8345. Min Act: -0.1700
Data Index: 3577148 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8658. Min Act: -0.1700
Data Index: 7043117 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8970. Min Act: -0.1700
Data Index: 925159 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.8033. Min Act: -0.1700
Data Index: 2206711 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.7720. Min Act: -0.1700
Data Index: 7247316 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.7095. Min Act: -0.1700
Data Index: 3402166 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.7408. Min Act: -0.1700
Data Index: 8713703 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2408. Min Range: -7.2408
Max Act: 6.7095. Min Act: -0.1700
Data Index: 709661 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19