Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.4092. Min Act: -0.1700
Data Index: 951042 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3935. Min Act: -0.1700
Data Index: 7769157 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3935. Min Act: -0.1700
Data Index: 4292198 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3307. Min Act: -0.1700
Data Index: 2334195 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3464. Min Act: -0.1700
Data Index: 8729907 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3151. Min Act: -0.1700
Data Index: 3793402 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.3151. Min Act: -0.1700
Data Index: 1750819 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2994. Min Act: -0.1700
Data Index: 3000502 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2837. Min Act: -0.1700
Data Index: 6492851 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2680. Min Act: -0.1700
Data Index: 1228866 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2837. Min Act: -0.1700
Data Index: 5803346 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2680. Min Act: -0.1700
Data Index: 5965410 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2522. Min Act: -0.1700
Data Index: 5523195 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2522. Min Act: -0.1700
Data Index: 3858091 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2522. Min Act: -0.1700
Data Index: 1863280 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2522. Min Act: -0.1700
Data Index: 1208678 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2208. Min Act: -0.1700
Data Index: 2271047 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2208. Min Act: -0.1700
Data Index: 8335710 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2208. Min Act: -0.1700
Data Index: 8275104 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4092. Min Range: -3.4092
Max Act: 3.2365. Min Act: -0.1700
Data Index: 8060508 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19