Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4744 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2205309 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.6524. Min Act: -0.1700
Data Index: 8160619 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 8474732 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1695
Data Index: 797059 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 471477 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6744109 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3915732 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3455394 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4337. Min Act: -0.1700
Data Index: 2809761 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4337. Min Act: -0.1700
Data Index: 5449442 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 4076702 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 6098622 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 670991 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6638613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 97403 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 4270506 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4024. Min Act: -0.1700
Data Index: 1915714 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.3712. Min Act: -0.1700
Data Index: 6129834 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.3712. Min Act: -0.1700
Data Index: 2919245 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.3712. Min Act: -0.1700
Data Index: 2142113 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19