Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.4537. Min Act: -0.1700
Data Index: 6764186 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.4225. Min Act: -0.1700
Data Index: 5845805 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.3287. Min Act: -0.1700
Data Index: 6286927 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.2662. Min Act: -0.1700
Data Index: 6492481 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.2350. Min Act: -0.1700
Data Index: 3155394 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.1412. Min Act: -0.1700
Data Index: 3292783 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.1100. Min Act: -0.1700
Data Index: 4189122 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0787. Min Act: -0.1700
Data Index: 4613181 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0787. Min Act: -0.1700
Data Index: 3508714 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.1100. Min Act: -0.1700
Data Index: 791137 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0475. Min Act: -0.1700
Data Index: 706181 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0475. Min Act: -0.1700
Data Index: 3739469 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0787. Min Act: -0.1700
Data Index: 6005113 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0475. Min Act: -0.1700
Data Index: 3824844 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4537. Min Range: -5.4537
Max Act: 4.9850. Min Act: -0.1700
Data Index: 6951706 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0162. Min Act: -0.1700
Data Index: 633407 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4537. Min Range: -5.4537
Max Act: 4.9850. Min Act: -0.1700
Data Index: 260881 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0162. Min Act: -0.1700
Data Index: 1913519 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0475. Min Act: -0.1700
Data Index: 6988605 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4537. Min Range: -5.4537
Max Act: 5.0162. Min Act: -0.1700
Data Index: 7804427 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19