Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1013 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.9601. Min Act: -0.1700
Data Index: 1761760 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8664. Min Act: -0.1700
Data Index: 4103124 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8351. Min Act: -0.1700
Data Index: 3797138 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8351. Min Act: -0.1700
Data Index: 6430559 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 5471227 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8039. Min Act: -0.1700
Data Index: 5951051 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8039. Min Act: -0.1700
Data Index: 4845476 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.8039. Min Act: -0.1700
Data Index: 4131522 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 5263 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 6954567 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 1888159 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 7407160 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 6719136 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7726. Min Act: -0.1700
Data Index: 3548038 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7414. Min Act: -0.1700
Data Index: 3489364 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7414. Min Act: -0.1700
Data Index: 2808856 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7414. Min Act: -0.1700
Data Index: 833255 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7101. Min Act: -0.1700
Data Index: 2793748 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7414. Min Act: -0.1700
Data Index: 476366 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9601. Min Range: -4.9601
Max Act: 4.7414. Min Act: -0.1700
Data Index: 6116146 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19