Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.9710. Min Act: -0.1700
Data Index: 4807708 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.4085. Min Act: -0.1700
Data Index: 6853420 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.3773. Min Act: -0.1700
Data Index: 1527649 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.3460. Min Act: -0.1700
Data Index: 7588434 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.3148. Min Act: -0.1700
Data Index: 6299673 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.3148. Min Act: -0.1700
Data Index: 1958966 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.2523. Min Act: -0.1700
Data Index: 21702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.2835. Min Act: -0.1700
Data Index: 4152091 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.2523. Min Act: -0.1700
Data Index: 4939555 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.2210. Min Act: -0.1700
Data Index: 5723062 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1898. Min Act: -0.1700
Data Index: 3843687 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1898. Min Act: -0.1700
Data Index: 2509913 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1272. Min Act: -0.1700
Data Index: 4152092 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1585. Min Act: -0.1700
Data Index: 4992587 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1272. Min Act: -0.1700
Data Index: 4954517 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1272. Min Act: -0.1700
Data Index: 5028839 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.0960. Min Act: -0.1700
Data Index: 4954507 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1272. Min Act: -0.1700
Data Index: 2987603 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.1272. Min Act: -0.1700
Data Index: 5028840 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9710. Min Range: -4.9710
Max Act: 4.0960. Min Act: -0.1700
Data Index: 5667806 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19