Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.6085. Min Act: -0.1700
Data Index: 4730745 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.5460. Min Act: -0.1662
Data Index: 6089090 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.4835. Min Act: -0.1700
Data Index: 8465043 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.2022. Min Act: -0.1700
Data Index: 2077020 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.1397. Min Act: -0.1700
Data Index: 285090 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7635866 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5605359 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7936285 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6849179 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6085. Min Range: -5.6085
Max Act: 5.0460. Min Act: -0.1691
Data Index: 816065 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.9835. Min Act: -0.1700
Data Index: 963510 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.9522. Min Act: -0.1700
Data Index: 2189453 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8897. Min Act: -0.1537
Data Index: 7117599 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8585. Min Act: -0.1700
Data Index: 3420940 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8897. Min Act: -0.1697
Data Index: 7650595 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8585. Min Act: -0.1676
Data Index: 3372006 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.7647. Min Act: -0.1700
Data Index: 8095777 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8272. Min Act: -0.1700
Data Index: 4507655 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.7960. Min Act: -0.1700
Data Index: 5972551 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6085. Min Range: -5.6085
Max Act: 4.8272. Min Act: -0.1700
Data Index: 4611410 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19