Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3365. Min Range: -5.3365
Max Act: 5.3365. Min Act: -0.1700
Data Index: 3132029 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3365. Min Range: -5.3365
Max Act: 5.2115. Min Act: -0.1700
Data Index: 1659638 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3365. Min Range: -5.3365
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3994329 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4517692 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.8990. Min Act: -0.1700
Data Index: 7028111 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.8365. Min Act: -0.1700
Data Index: 3164968 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4173033 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4861592 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7740. Min Act: -0.1700
Data Index: 8240480 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3196663 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7740. Min Act: -0.1700
Data Index: 8176890 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7740. Min Act: -0.1700
Data Index: 1380681 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7740. Min Act: -0.1700
Data Index: 3491967 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7427. Min Act: -0.1700
Data Index: 4364033 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.6802. Min Act: -0.1699
Data Index: 2081741 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.7115. Min Act: -0.1700
Data Index: 2285125 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.6802. Min Act: -0.1700
Data Index: 817443 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.6802. Min Act: -0.1700
Data Index: 6436576 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.6802. Min Act: -0.1700
Data Index: 2419856 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3365. Min Range: -5.3365
Max Act: 4.6177. Min Act: -0.1700
Data Index: 7018014 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19