Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.5939. Min Act: -0.1700
Data Index: 7712055 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.5626. Min Act: -0.1700
Data Index: 1494169 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.5314. Min Act: -0.1700
Data Index: 6288929 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.5001. Min Act: -0.1699
Data Index: 3738952 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.5001. Min Act: -0.1700
Data Index: 2737261 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 8563590 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 6329752 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 1461281 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 7255813 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 3208130 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 3216567 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4376. Min Act: -0.1700
Data Index: 385275 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4376. Min Act: -0.1700
Data Index: 485371 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4376. Min Act: -0.1700
Data Index: 3329991 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.4064. Min Act: -0.1700
Data Index: 6922126 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.3751. Min Act: -0.1700
Data Index: 8758195 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.3751. Min Act: -0.1700
Data Index: 8105160 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.3439. Min Act: -0.1700
Data Index: 2160289 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.3439. Min Act: -0.1700
Data Index: 1148420 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5939. Min Range: -5.5939
Max Act: 5.3439. Min Act: -0.1700
Data Index: 897296 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19