Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.2761. Min Act: -0.1700
Data Index: 3631490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.1198. Min Act: -0.1700
Data Index: 3732187 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.1198. Min Act: -0.1700
Data Index: 5199689 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.1198. Min Act: -0.1700
Data Index: 7793948 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0885. Min Act: -0.1700
Data Index: 2693555 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0573. Min Act: -0.1700
Data Index: 5156735 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0885. Min Act: -0.1700
Data Index: 8137359 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0573. Min Act: -0.1700
Data Index: 5995798 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0573. Min Act: -0.1700
Data Index: 156503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0573. Min Act: -0.1699
Data Index: 5066737 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 5035033 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0885. Min Act: -0.1700
Data Index: 4564087 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0573. Min Act: -0.1700
Data Index: 4097842 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 700652 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 6426498 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 3273291 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 3342845 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2761. Min Range: -4.2761
Max Act: 3.9948. Min Act: -0.1700
Data Index: 1005358 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 3376739 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2761. Min Range: -4.2761
Max Act: 4.0260. Min Act: -0.1700
Data Index: 2022191 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19