Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7489. Min Range: -7.7489
Max Act: 7.7489. Min Act: -0.1700
Data Index: 3623500 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7489. Min Range: -7.7489
Max Act: 7.4677. Min Act: -0.1700
Data Index: 4019535 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7489. Min Range: -7.7489
Max Act: 7.3739. Min Act: -0.1700
Data Index: 1151345 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7489. Min Range: -7.7489
Max Act: 7.1864. Min Act: -0.1700
Data Index: 8642828 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7489. Min Range: -7.7489
Max Act: 7.0614. Min Act: -0.1700
Data Index: 1844721 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9677. Min Act: -0.1700
Data Index: 7900690 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9989. Min Act: -0.1700
Data Index: 6729171 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9052. Min Act: -0.1700
Data Index: 3453083 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9364. Min Act: -0.1700
Data Index: 1844716 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9052. Min Act: -0.1700
Data Index: 976363 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.9052. Min Act: -0.1700
Data Index: 2623236 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.8739. Min Act: -0.1700
Data Index: 3453091 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.8114. Min Act: -0.1700
Data Index: 6140013 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.8114. Min Act: -0.1700
Data Index: 1256132 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.8114. Min Act: -0.1700
Data Index: 4092027 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.7802. Min Act: -0.1700
Data Index: 4035265 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.7802. Min Act: -0.1700
Data Index: 6354202 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.7489. Min Act: -0.1700
Data Index: 2195702 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.7802. Min Act: -0.1700
Data Index: 7987965 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7489. Min Range: -7.7489
Max Act: 6.7489. Min Act: -0.1700
Data Index: 3453103 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19