Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 705 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.5699. Min Act: -0.1700
Data Index: 896933 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.5074. Min Act: -0.1700
Data Index: 8060304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.5074. Min Act: -0.1700
Data Index: 702602 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.4761. Min Act: -0.1700
Data Index: 5707289 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.4761. Min Act: -0.1700
Data Index: 2998445 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.4449. Min Act: -0.1700
Data Index: 2195307 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.4449. Min Act: -0.1700
Data Index: 6073193 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.4136. Min Act: -0.1700
Data Index: 3610443 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3824. Min Act: -0.1700
Data Index: 103779 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3824. Min Act: -0.1700
Data Index: 1983143 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 6415006 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 7540433 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3824. Min Act: -0.1700
Data Index: 6291820 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 947515 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3199. Min Act: -0.1700
Data Index: 5679119 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 7814969 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3824. Min Act: -0.1700
Data Index: 8016592 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 4782331 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3511. Min Act: -0.1700
Data Index: 5229401 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5699. Min Range: -4.5699
Max Act: 4.3199. Min Act: -0.1700
Data Index: 6689306 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19