Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5856. Min Act: -0.1700
Data Index: 1869685 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5856. Min Act: -0.1700
Data Index: 1473629 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.6168. Min Act: -0.1700
Data Index: 2808355 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5060161 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 3886153 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1699
Data Index: 1497296 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 2889537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 6312210 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 2777029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 5717801 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 2534401 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 675788 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 2732110 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 7477957 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 4198353 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1699
Data Index: 2110373 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4293. Min Act: -0.1700
Data Index: 2024984 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4293. Min Act: -0.1700
Data Index: 492877 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4293. Min Act: -0.1700
Data Index: 2991275 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4293. Min Act: -0.1700
Data Index: 3297066 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19