Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 118 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3165. Min Range: -4.3165
Max Act: 4.3165. Min Act: -0.1700
Data Index: 8573249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3165. Min Range: -4.3165
Max Act: 4.0665. Min Act: -0.1700
Data Index: 943696 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3165. Min Range: -4.3165
Max Act: 4.0665. Min Act: -0.1700
Data Index: 5126984 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3165. Min Range: -4.3165
Max Act: 4.0039. Min Act: -0.1700
Data Index: 7169575 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.9101. Min Act: -0.1700
Data Index: 4394676 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.9101. Min Act: -0.1700
Data Index: 2320089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.9101. Min Act: -0.1700
Data Index: 3807799 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8789. Min Act: -0.1700
Data Index: 4548979 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3755315 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8789. Min Act: -0.1700
Data Index: 4346222 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 7448533 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 8787393 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 4514418 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8789. Min Act: -0.1700
Data Index: 6643473 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3530835 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.7851. Min Act: -0.1700
Data Index: 3870354 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3016858 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8163. Min Act: -0.1700
Data Index: 3171411 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8476. Min Act: -0.1700
Data Index: 5502683 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3165. Min Range: -4.3165
Max Act: 3.8163. Min Act: -0.1700
Data Index: 8647898 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19