Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0462. Min Range: -5.0462
Max Act: 5.0462. Min Act: -0.1700
Data Index: 3881256 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0462. Min Range: -5.0462
Max Act: 5.0149. Min Act: -0.1699
Data Index: 4152649 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9837. Min Act: -0.1694
Data Index: 4152652 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 3773099 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 5561828 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 4485285 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 16156 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 5246017 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1680
Data Index: 2711075 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 2284512 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.9212. Min Act: -0.1700
Data Index: 1692353 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 4152651 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 1616736 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 5327756 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 2030311 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 7911728 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8587. Min Act: -0.1700
Data Index: 2107316 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8587. Min Act: -0.1700
Data Index: 2090953 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8587. Min Act: -0.1700
Data Index: 5554051 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0462. Min Range: -5.0462
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3791386 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19