Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2480. Min Range: -7.2480
Max Act: 7.2480. Min Act: -0.1700
Data Index: 7738224 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2480. Min Range: -7.2480
Max Act: 7.1543. Min Act: -0.1700
Data Index: 5830699 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.9043. Min Act: -0.1700
Data Index: 2060485 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.8105. Min Act: -0.1700
Data Index: 7693023 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.7168. Min Act: -0.1700
Data Index: 434929 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.7480. Min Act: -0.1700
Data Index: 2952485 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.7168. Min Act: -0.1700
Data Index: 4147526 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.7168. Min Act: -0.1700
Data Index: 895622 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6855. Min Act: -0.1700
Data Index: 1977402 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3151029 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2859912 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.7168. Min Act: -0.1700
Data Index: 2859909 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6543. Min Act: -0.1700
Data Index: 2859910 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6543. Min Act: -0.1700
Data Index: 6764284 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6543. Min Act: -0.1700
Data Index: 5592099 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6230. Min Act: -0.1700
Data Index: 990593 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.6230. Min Act: -0.1700
Data Index: 7708954 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.5605. Min Act: -0.1700
Data Index: 1242826 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.5605. Min Act: -0.1700
Data Index: 7907773 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2480. Min Range: -7.2480
Max Act: 6.4980. Min Act: -0.1700
Data Index: 3369469 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19